© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29146
    Prev
    Next
    INDEX
    Explanations

    descriptive states and processes

    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
    ي
    0.47
     ак
    0.45
     ሃ
    0.45
     الأ
    0.44
    }).
    0.44
    纡
    0.44
     и
    0.43
    𝐋
    0.43
    Removed
    0.43
     Л
    0.42
    POSITIVE LOGITS
    ifelse
    0.53
     Comrade
    0.48
     Harb
    0.47
     suami
    0.46
    drž
    0.45
     knob
    0.43
     mutu
    0.43
     forefathers
    0.42
     보여
    0.41
     évidence
    0.41
    Activations Density 0.003%

    No Known Activations