© 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. 20895
    Prev
    Next
    INDEX
    Explanations

    unique identifiers and codes

    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
    }".
    0.44
     rumor
    0.40
     collaborator
    0.39
     rumour
    0.38
     collaborating
    0.38
    ,"
    0.38
    ":(
    0.37
     authorization
    0.37
    ,'"
    0.37
     collaborators
    0.37
    POSITIVE LOGITS
    IC
    0.43
    JC
    0.42
    Ć
    0.41
    InEx
    0.41
    CTR
    0.40
     класси
    0.40
     Example
    0.40
    INS
    0.40
     \#
    0.40
     сот
    0.40
    Activations Density 0.019%

    No Known Activations