© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 50618
    Prev
    Next
    INDEX
    Explanations

    month of, range of, tied to, moment longer

    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_65k_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
    alo
    0.48
    rine
    0.47
    pe
    0.45
    0.44
    rena
    0.43
    ______
    0.43
    bh
    0.42
    diri
    0.42
     ______
    0.42
    dh
    0.42
    POSITIVE LOGITS
     levies
    0.50
     enraged
    0.49
    Needless
    0.47
    RequestBody
    0.46
     bygone
    0.46
     breaches
    0.45
     treacherous
    0.45
     whereabouts
    0.44
     zast
    0.44
     credential
    0.43
    Activations Density 0.003%

    No Known Activations