© 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. 132501
    Prev
    Next
    INDEX
    Explanations

    data or information

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

    follows specific keywords

    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
     道
    0.48
    コール
    0.47
    Tama
    0.47
    পান
    0.47
    न
    0.46
    リ
    0.46
    濂
    0.46
    कांग्रेस
    0.45
    Haven
    0.45
    Ω
    0.45
    POSITIVE LOGITS
     ergodic
    0.45
    essoal
    0.44
    则是
    0.44
    alty
    0.43
    ));
    0.43
     ),
    0.42
     folgende
    0.42
    aly
    0.42
     maka
    0.41
    oon
    0.41
    Activations Density 0.000%

    No Known Activations