© 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. 78332
    Prev
    Next
    INDEX
    Explanations

    "how to" titles and topics

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

    of Seven Killings, Called Empire, Price of Salt

    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
     fatti
    0.35
     constituencies
    0.35
    
    0.34
     coexist
    0.34
     conto
    0.34
     Compaq
    0.33
     thats
    0.33
     prerogative
    0.33
     patric
    0.33
     bridle
    0.33
    POSITIVE LOGITS
    ut
    0.41
    ak
    0.40
    y
    0.39
    ong
    0.39
    áf
    0.37
    }(
    0.37
    7
    0.37
    temperatur
    0.37
    T
    0.36
    ahrung
    0.36
    Activations Density 0.049%

    No Known Activations