© 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. 127311
    Prev
    Next
    INDEX
    Explanations

    information and communication

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

    common concern

    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
    作為
    0.45
    等地
    0.44
    话
    0.42
    рио
    0.41
     самостоятельно
    0.40
    獃
    0.40
    یشہ
    0.39
    शक्ति
    0.39
    ให้กับ
    0.39
    findOrFail
    0.38
    POSITIVE LOGITS
     aws
    0.46
    1
    0.45
     recicl
    0.45
     went
    0.44
     tiež
    0.43
     Verbesser
    0.43
     Datenbank
    0.43
     cakes
    0.43
     oyunc
    0.43
     dez
    0.42
    Activations Density 0.000%

    No Known Activations