© 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. 197783
    Prev
    Next
    INDEX
    Explanations

    correlations and stories, macarons

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

    nodes and attributes

    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
     التمرين
    0.48
     эмне
    0.48
     thử
    0.47
     သ
    0.45
     cậu
    0.45
     αφού
    0.45
     Tactics
    0.45
     തന്നെ
    0.44
     hãy
    0.44
     অজ্ঞ
    0.44
    POSITIVE LOGITS
    pri
    0.43
     indefin
    0.41
    spr
    0.41
    comes
    0.41
     =
    0.40
    arching
    0.39
    ूप
    0.39
     freak
    0.39
    p
    0.39
     daytime
    0.39
    Activations Density 0.001%

    No Known Activations