© 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. 219588
    Prev
    Next
    INDEX
    Explanations

    Estate planning services

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

    seeking a, looking for

    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
    殇
    0.51
    殤
    0.51
    CASE
    0.49
    {*
    0.46
    筤
    0.46
    бую
    0.45
    RESULTS
    0.44
    atlar
    0.44
     conclude
    0.44
     радо
    0.44
    POSITIVE LOGITS
    y
    0.50
    v
    0.49
    ious
    0.48
    aj
    0.47
    es
    0.47
    ary
    0.46
     hy
    0.45
    ed
    0.45
    ous
    0.44
    ied
    0.44
    Activations Density 0.000%

    No Known Activations