© 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. 9235
    Prev
    Next
    INDEX
    Explanations

    the company, supplier

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

    Comes from

    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
    d
    0.56
    r
    0.55
    _
    0.52
    inko
    0.51
    il
    0.48
    ائیو
    0.48
    ri
    0.48
    ara
    0.48
    rava
    0.46
    ње
    0.46
    POSITIVE LOGITS
     卡
    0.50
     नु
    0.49
     nac
    0.48
     వివిధ
    0.47
    ährung
    0.46
     周
    0.46
    Flagge
    0.45
     spender
    0.45
     이슈
    0.45
     dto
    0.44
    Activations Density 0.000%

    No Known Activations