© 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. 17073
    Prev
    Next
    INDEX
    Explanations

    multilingual script and words

    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
    niger
    0.48
    ruption
    0.44
    ọ
    0.43
    oran
    0.42
    testimonial
    0.42
    ides
    0.42
    typeName
    0.41
    ilst
    0.41
     अचानक
    0.41
    new
    0.40
    POSITIVE LOGITS
    ोटेन
    0.40
    ेलो
    0.40
    णू
    0.40
     pousse
    0.40
     glyph
    0.38
    اث
    0.38
    ᒫ
    0.38
    িনবার্গ
    0.37
    쭤
    0.37
    жной
    0.37
    Activations Density 0.000%

    No Known Activations