© 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-65K
    7. 46289
    Prev
    Next
    INDEX
    Explanations

    loss after certain words

    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
    苷
    0.45
     tighten
    0.43
    Hochspringen
    0.43
    扦
    0.41
    细节
    0.40
     detail
    0.39
     성
    0.38
     prism
    0.38
    ษัท
    0.38
     Xác
    0.38
    POSITIVE LOGITS
    ERR
    0.53
    یس
    0.46
    ER
    0.45
    न
    0.45
    isodes
    0.44
    UL
    0.44
    TO
    0.43
    fledged
    0.43
    experienced
    0.42
     puerto
    0.42
    Activations Density 0.001%

    No Known Activations