© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57269
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags code‐specific tokens (function calls, identifiers, punctuation like `{`, `;`, string literals, etc.) that distinguish code from normal text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tog
    -0.84
    φυ
    -0.81
     ヴィトン
    -0.77
     вопрос
    -0.76
    служба
    -0.72
     garantir
    -0.72
     téléphone
    -0.71
    ínico
    -0.71
     maxime
    -0.71
    }}</
    -0.71
    POSITIVE LOGITS
     sesiones
    0.82
     waż
    0.81
    近くに
    0.77
     здоро
    0.74
     )
    0.74
     difíciles
    0.73
     monoc
    0.72
    サラ
    0.72
     turbulent
    0.71
    ingh
    0.71
    Activations Density 0.037%

    No Known Activations