© 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. 74183
    Prev
    Next
    INDEX
    Explanations

    email accounts

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

    certain actions or states

    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
     сыгра
    0.47
     चैम्पियन
    0.46
    靱
    0.46
    important
    0.42
    プレイ
    0.42
    韆
    0.42
     фонда
    0.42
    enzione
    0.41
     চ্যাম্প
    0.41
    district
    0.41
    POSITIVE LOGITS
     timescale
    0.50
     timescales
    0.46
     tiktok
    0.46
     Revit
    0.45
     eset
    0.45
     myself
    0.43
     እ
    0.43
     sanity
    0.41
     mimics
    0.41
    此同时
    0.41
    Activations Density 0.003%

    No Known Activations