© 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. 242289
    Prev
    Next
    INDEX
    Explanations

    causes another

    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
     schwer
    0.52
    נו
    0.51
     Karriere
    0.49
     seule
    0.47
    ました
    0.45
    ༨
    0.45
     Roasted
    0.45
     tetahi
    0.45
     FanDuel
    0.44
     జట్టు
    0.44
    POSITIVE LOGITS
     ιδ
    0.50
     پزش
    0.50
     而
    0.50
     已
    0.49
    obr
    0.49
    rif
    0.47
     ή
    0.47
    erald
    0.46
    andan
    0.46
    ibr
    0.46
    Activations Density 0.000%

    No Known Activations