© 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. 30639
    Prev
    Next
    INDEX
    Explanations

    prioritizing getting, managing extensions, customization

    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
    ustration
    0.49
    طه
    0.48
    ried
    0.46
    punk
    0.43
    }_{+}
    0.42
    뀌
    0.42
     tantal
    0.42
     sabotage
    0.42
    kraft
    0.42
    pc
    0.41
    POSITIVE LOGITS
    0.52
    ையின்
    0.48
    FIND
    0.48
    ParentObject
    0.47
    鸮
    0.47
    WQ
    0.47
    ┇
    0.46
     Merlin
    0.46
    KH
    0.45
    Drugs
    0.45
    Activations Density 0.013%

    No Known Activations