© 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. 200061
    Prev
    Next
    INDEX
    Explanations

    streaming recommendations

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

    technical qualifiers and descriptors

    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
    र्मेंद्र
    0.43
    Punch
    0.42
    HG
    0.42
    TECH
    0.42
     Punch
    0.42
     HG
    0.42
     சேன
    0.42
     整
    0.41
     Denne
    0.41
    这款
    0.40
    POSITIVE LOGITS
    ри
    0.53
     disordered
    0.48
     били
    0.46
     vicious
    0.44
    ილ
    0.42
    iname
    0.42
    𝘃
    0.42
    하도록
    0.42
    V
    0.42
    ilateral
    0.41
    Activations Density 0.000%

    No Known Activations