© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 125864
    Prev
    Next
    INDEX
    Explanations

    actions following states

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

    troubleshooting and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adau
    0.48
    attoo
    0.46
    DS
    0.45
    9
    0.45
    7
    0.44
    dS
    0.44
    sad
    0.44
    6
    0.44
    е
    0.44
    HAO
    0.43
    POSITIVE LOGITS
     estrutura
    0.48
    车型
    0.46
     금액
    0.44
    ুটি
    0.43
     estruturas
    0.43
     parámetro
    0.43
     montant
    0.43
     منطقة
    0.43
     funcional
    0.42
     beni
    0.42
    Activations Density 0.001%

    No Known Activations