© 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. 77446
    Prev
    Next
    INDEX
    Explanations

    investigate

    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
    ä
    0.80
    ної
    0.72
    ется
    0.69
     Në
    0.69
    <0xA7>
    0.68
    ním
    0.68
     kunnen
    0.66
     mówi
    0.66
     Zuid
    0.65
    <0xBC>
    0.64
    POSITIVE LOGITS
    ב
    1.07
    ה
    1.06
     inquiries
    0.99
    g
    0.92
    ک
    0.90
    મ
    0.90
    স
    0.88
    Investigation
    0.88
    ก
    0.85
    К
    0.84
    Activations Density 0.011%

    No Known Activations