© 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. 62645
    Prev
    Next
    INDEX
    Explanations

    division input stands grant

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

    Supply chains

    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
    ت
    0.58
    +
    0.56
    -
    0.52
    يم
    0.52
    米
    0.50
    ف
    0.49
    غ
    0.47
    سم
    0.47
     im
    0.46
     ফাই
    0.46
    POSITIVE LOGITS
    siswa
    0.49
     나올
    0.49
     ۋ
    0.46
    prost
    0.46
    yuan
    0.46
     دیں
    0.45
    është
    0.45
    ⾏
    0.44
    GetAxis
    0.43
     کررہے
    0.43
    Activations Density 0.000%

    No Known Activations