© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47646
    Prev
    Next
    INDEX
    Explanations

    specific subjects in lists

    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
    渙
    0.45
    壓
    0.44
     Cual
    0.43
     IHS
    0.42
     Registered
    0.42
     Registers
    0.42
     hilltop
    0.42
     Coinbase
    0.41
     PST
    0.41
     ምክንያት
    0.41
    POSITIVE LOGITS
    su
    0.48
    ству
    0.46
     interess
    0.45
    !]
    0.44
     персона
    0.44
     перспек
    0.44
    зов
    0.44
    。
    0.44
    Со
    0.43
    !'
    0.43
    Activations Density 0.001%

    No Known Activations