© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12237
    Prev
    Next
    INDEX
    Explanations

    left, right, 2, red, black

    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
    ༔
    0.58
    ฟ
    0.54
    ד
    0.54
    ัล
    0.54
    ร
    0.50
    ה
    0.49
    ל
    0.48
    ༨
    0.47
    ężczy
    0.47
    קי
    0.47
    POSITIVE LOGITS
     also
    0.52
     provides
    0.48
     from
    0.48
     only
    0.47
     with
    0.46
     inoltre
    0.46
     serves
    0.46
     increases
    0.45
     home
    0.45
     Class
    0.45
    Activations Density 0.016%

    No Known Activations