© 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. 206320
    Prev
    Next
    INDEX
    Explanations

    civic hopes OR Mr X

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

    password prompts

    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
    IsIn
    0.48
    झ
    0.48
    ప్పటి
    0.47
     on
    0.46
    通讯
    0.44
     במס
    0.44
    鬏
    0.43
    Bola
    0.43
     ঝ
    0.43
    OfDeath
    0.43
    POSITIVE LOGITS
    capture
    0.51
     expansive
    0.49
    iga
    0.48
     सहज
    0.48
    ante
    0.46
     crea
    0.46
     ฟรี
    0.46
    sandbox
    0.45
    auh
    0.45
     expressive
    0.45
    Activations Density 0.001%

    No Known Activations