© 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. 135814
    Prev
    Next
    INDEX
    Explanations

    assets and billions

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

    notes or observations

    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
    谄
    0.53
     geralmente
    0.52
     Biasanya
    0.52
    𝘵
    0.50
     hará
    0.50
    фин
    0.50
    йи
    0.49
    腱
    0.49
     comerciantes
    0.48
     SPINE
    0.48
    POSITIVE LOGITS
     onsite
    0.52
     አን
    0.47
    uk
    0.44
     judgements
    0.44
    ene
    0.43
     burning
    0.42
    നായി
    0.42
    s
    0.42
    oue
    0.40
     relocated
    0.40
    Activations Density 0.000%

    No Known Activations