© 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. 204551
    Prev
    Next
    INDEX
    Explanations

    like

    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
     salvar
    0.55
     salva
    0.53
     salvare
    0.52
     člov
    0.51
     klinik
    0.51
     člove
    0.51
    <unused316>
    0.50
     människ
    0.50
    <unused698>
    0.50
     pasajeros
    0.50
    POSITIVE LOGITS
    0.52
    r
    0.51
    OP
    0.47
    Ontario
    0.46
    th
    0.43
    op
    0.43
    R
    0.42
    ↵↵
    0.42
    ร
    0.42
    UP
    0.40
    Activations Density 0.004%

    No Known Activations