© 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. 123009
    Prev
    Next
    INDEX
    Explanations

    specific concepts followed by elaboration

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

    obtained licenses, plucked from, criminal?

    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
    0.57
    、
    0.50
     ਵ
    0.47
    雪
    0.46
    agnetic
    0.45
     jealousy
    0.43
    することは
    0.43
    モ
    0.43
    άν
    0.42
     snow
    0.42
    POSITIVE LOGITS
     bened
    0.55
     insegn
    0.53
     Certain
    0.52
    పాటు
    0.51
     Тут
    0.51
     देयर
    0.50
     prue
    0.49
    న్స్‌
    0.48
     Obtained
    0.47
    ringstream
    0.47
    Activations Density 0.000%

    No Known Activations