© 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. 172706
    Prev
    Next
    INDEX
    Explanations

    community members

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

    explicitly or exploited

    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
    LLS
    0.50
    Ag
    0.47
    竄
    0.47
    benzene
    0.44
     Patients
    0.43
     Industri
    0.42
     Essex
    0.41
    ЕНИЕ
    0.41
     patients
    0.41
     Ulster
    0.41
    POSITIVE LOGITS
    🐡
    0.53
     sezon
    0.52
     ወቅ
    0.49
    に向けて
    0.49
     시즌
    0.48
    𒉰
    0.48
    だよ
    0.48
    🐠
    0.48
     تعلیم
    0.47
    zco
    0.47
    Activations Density 0.001%

    No Known Activations