© 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. 183846
    Prev
    Next
    INDEX
    Explanations

    bornfurtherpets

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

    `thumb` and `Impact`

    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
    华
    0.48
     nombre
    0.45
    فر
    0.44
    上了
    0.44
     woord
    0.44
     ništa
    0.44
    فين
    0.43
     aberta
    0.41
    ώ
    0.41
    貳
    0.41
    POSITIVE LOGITS
    াহিনী
    0.48
    TEMP
    0.46
    SQLALCHEMY
    0.45
    ATO
    0.45
    nosi
    0.45
    রুখ
    0.45
    >:</
    0.44
    働
    0.44
     колек
    0.44
    lusconi
    0.43
    Activations Density 0.000%

    No Known Activations