© 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. 55429
    Prev
    Next
    INDEX
    Explanations

    air receiver

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

    list items, descriptions

    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
    ৩৮
    0.53
     ちゃ
    0.50
     загру
    0.49
    難しい
    0.49
    _'.$
    0.48
    妺
    0.48
     dignit
    0.48
     Helens
    0.47
    教師
    0.47
    弟弟
    0.47
    POSITIVE LOGITS
    رات
    0.49
    ries
    0.42
    ಾರ್ಟ
    0.41
    ris
    0.40
    merged
    0.40
     Risiko
    0.40
     Risk
    0.39
     Moderators
    0.39
    ൯
    0.39
    LR
    0.39
    Activations Density 0.000%

    No Known Activations