© 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. 15867
    Prev
    Next
    INDEX
    Explanations

    mergers, acquisitions, awards, achievements

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

    here's how a

    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
    する
    0.41
    させる
    0.41
    使
    0.40
     edilmesi
    0.39
    测
    0.39
     하여
    0.39
    하는
    0.38
    指出
    0.37
     inad
    0.37
    akaran
    0.37
    POSITIVE LOGITS
     udało
    0.53
     было
    0.52
     wasn
    0.51
     был
    0.50
     была
    0.50
     большая
    0.48
     были
    0.46
     została
    0.46
     habíamos
    0.45
     був
    0.45
    Activations Density 0.000%

    No Known Activations