© 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. 125817
    Prev
    Next
    INDEX
    Explanations

    not for the easily offended

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

    numbers, sagari, avoid, jingle, conflict

    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
    Л
    0.48
     ম্যান
    0.45
    çek
    0.44
    Holy
    0.43
    Santos
    0.43
    view
    0.43
     Früh
    0.42
     دي
    0.42
     Alphon
    0.42
    Для
    0.41
    POSITIVE LOGITS
    ारी
    0.48
    cuterie
    0.46
    掾
    0.44
    ல்லாம்
    0.44
    ারি
    0.42
    ीत
    0.42
    च्चय
    0.42
    ारा
    0.42
    iciable
    0.42
    串
    0.41
    Activations Density 0.001%

    No Known Activations