© 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. 88975
    Prev
    Next
    INDEX
    Explanations

    country populations restored

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

    or alternatives

    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
     adolescent
    0.49
    مپ
    0.43
    )$,
    0.43
     procedures
    0.43
    ای
    0.42
     Methods
    0.42
     adolescence
    0.42
    ز
    0.42
    ش
    0.41
     Iron
    0.41
    POSITIVE LOGITS
     ἢ
    0.52
     yoki
    0.51
     veya
    0.50
    schlag
    0.48
     обще
    0.48
     அல்லது
    0.47
    cimento
    0.47
    敦
    0.46
     alebo
    0.46
    rijke
    0.46
    Activations Density 0.000%

    No Known Activations