© 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. 40647
    Prev
    Next
    INDEX
    Explanations

    tragically forced

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

    causes problems or explains actions

    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
     `<
    0.46
     irregularities
    0.45
    ᅭ
    0.41
    (`<
    0.41
     informally
    0.41
     Neend
    0.40
    嫋
    0.40
     otev
    0.40
     correctes
    0.40
     visualiser
    0.40
    POSITIVE LOGITS
    espresso
    0.46
    s
    0.45
    getBlueTeam
    0.44
     হন্ড
    0.42
     पैसों
    0.41
    undant
    0.41
    ósfera
    0.41
    ecan
    0.41
     プ
    0.41
     JCV
    0.40
    Activations Density 0.000%

    No Known Activations