© 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. 15967
    Prev
    Next
    INDEX
    Explanations

    here and there or coming

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

    purpose, why, how, horrific

    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
     होईल
    0.43
     Lorenz
    0.41
    iper
    0.40
    goes
    0.39
     दौड़
    0.39
     ይመ
    0.38
     বাড়বে
    0.38
    聲
    0.38
     लगेगा
    0.38
     lags
    0.38
    POSITIVE LOGITS
     이곳
    0.72
     এসেছেন
    0.68
     arrived
    0.64
     sedang
    0.61
    Chosen
    0.61
     đang
    0.60
    来到
    0.59
     এসেছি
    0.59
    来た
    0.59
     여기가
    0.59
    Activations Density 0.085%

    No Known Activations