© 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. 238663
    Prev
    Next
    INDEX
    Explanations

    essays and paragraphs

    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
    மல்
    0.63
    eous
    0.52
    ugía
    0.51
    ಂಥ
    0.51
    werben
    0.50
    铳
    0.49
    はこの
    0.49
    writeFile
    0.48
    TEGER
    0.48
    명의
    0.48
    POSITIVE LOGITS
     Fault
    0.53
     Edward
    0.52
     Affordable
    0.50
     a
    0.49
     Oil
    0.48
     oil
    0.47
     an
    0.47
     Motion
    0.46
     the
    0.46
     Ultimate
    0.46
    Activations Density 0.001%

    No Known Activations