© 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. 44838
    Prev
    Next
    INDEX
    Explanations

    power comes

    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
    $.\
    0.46
     pess
    0.42
    َی
    0.42
    ี
    0.42
     bitte
    0.41
    ̀i
    0.41
    ೭
    0.41
    🎓
    0.41
    ٣
    0.40
    ೩
    0.40
    POSITIVE LOGITS
    రీలు
    0.49
     zarówno
    0.47
     facades
    0.41
     barges
    0.40
    aos
    0.40
    ={()
    0.39
    led
    0.39
    mars
    0.39
     endlessly
    0.38
    पाउंड
    0.38
    Activations Density 0.001%

    No Known Activations