© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17657
    Prev
    Next
    INDEX
    Explanations

    Circulars, junk mail, property taxes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     przedsi
    0.31
     travaux
    0.31
     பல்
    0.30
     accidentes
    0.29
     측정
    0.29
     problema
    0.29
    थ
    0.29
    학
    0.29
    URS
    0.28
     устра
    0.27
    POSITIVE LOGITS
     robes
    0.39
     alcohols
    0.34
     livestream
    0.34
     microbes
    0.34
    inoa
    0.34
     ador
    0.32
    ıyordu
    0.32
     adoration
    0.32
     dunes
    0.31
     identities
    0.31
    Activations Density 0.000%

    No Known Activations