© 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. 44132
    Prev
    Next
    INDEX
    Explanations

    specific beginnings of sentences

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

    asking questions and seeking access

    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
    ﾚ
    0.48
    0
    0.47
    性和
    0.46
    URANCE
    0.45
    REX
    0.45
    かしい
    0.44
    combined
    0.44
    ᱘
    0.43
    ᅨ
    0.42
    性が
    0.42
    POSITIVE LOGITS
     Wolverhampton
    0.47
     zarządz
    0.45
     Wals
    0.44
     oars
    0.43
     такая
    0.42
    oldsymbol
    0.41
     foliis
    0.41
    کان
    0.41
     Alpes
    0.40
     dopamine
    0.40
    Activations Density 0.001%

    No Known Activations