© 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. 79364
    Prev
    Next
    INDEX
    Explanations

    campervan road

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

    casting, JavaScript, list, offering, suitable, Divide, acts

    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
    אם
    0.53
     subdue
    0.51
    präsident
    0.50
     哦
    0.50
    म्या
    0.49
    เตอร์
    0.49
     것을
    0.49
     attest
    0.47
     accede
    0.46
     אבל
    0.45
    POSITIVE LOGITS
    ာ
    0.49
    r
    0.48
    ισ
    0.48
    ion
    0.44
     neighbouring
    0.44
    emb
    0.44
    groomed
    0.43
    cyclic
    0.43
     homology
    0.42
     Kubo
    0.42
    Activations Density 0.000%

    No Known Activations