© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72919
    Prev
    Next
    INDEX
    Explanations

    event specific details

    np_acts-logits-general · gemini-2.5-flash-lite

    MEMORANDUM subject details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deepcopy
    0.44
    ٤
    0.41
    tabControl
    0.40
    Ω
    0.39
    DMSO
    0.39
    IA
    0.37
     غير
    0.37
    coelastic
    0.37
    %%%%%%%%%%%%%%%%
    0.37
    oS
    0.37
    POSITIVE LOGITS
     offender
    0.46
     culprit
    0.45
     interviewee
    0.43
     reason
    0.42
     reward
    0.42
     tactic
    0.42
     sentence
    0.42
     date
    0.41
     lesson
    0.41
     taskId
    0.41
    Activations Density 0.080%

    No Known Activations