© 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. 78552
    Prev
    Next
    INDEX
    Explanations

    specifically originating from

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

    future actions and outcomes

    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
    †
    0.50
     resemblance
    0.46
    jord
    0.45
    aboard
    0.45
     paste
    0.45
    Jen
    0.44
    v
    0.43
     we
    0.43
    o
    0.43
    |
    0.43
    POSITIVE LOGITS
     entidade
    0.55
    ائیں
    0.52
     isti
    0.51
     പരിശീല
    0.51
     últ
    0.51
    एगी
    0.51
     جوړونکو
    0.50
     predecess
    0.50
    സർ
    0.50
     mixts
    0.50
    Activations Density 0.000%

    No Known Activations