© 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. 61968
    Prev
    Next
    INDEX
    Explanations

    locations, business, or technical terms

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

    caps negotiation

    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
     అనంతరం
    0.51
    మన్
    0.48
    酚
    0.47
    ſed
    0.47
     भत्ता
    0.46
    जनक
    0.46
    ్వర
    0.46
     उत्पादन
    0.46
    สต์
    0.44
    риал
    0.44
    POSITIVE LOGITS
    xa
    0.54
    in
    0.53
    saya
    0.52
    Q
    0.52
     saya
    0.51
     escond
    0.51
     mung
    0.50
     xa
    0.50
     sekund
    0.49
     rojo
    0.48
    Activations Density 0.000%

    No Known Activations