© 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. 29794
    Prev
    Next
    INDEX
    Explanations

    Read More or Read the full story

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

    news and updates

    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
    ೧
    0.52
    ूंकि
    0.45
    ติดตั้ง
    0.44
    붕
    0.44
    𝗯
    0.44
    ֿ
    0.43
    𝟮
    0.43
    ➀
    0.43
    }\|
    0.43
     บอก
    0.42
    POSITIVE LOGITS
    faction
    0.46
     phen
    0.42
    asm
    0.41
     peace
    0.41
    mai
    0.41
    phen
    0.41
    peace
    0.40
     plentiful
    0.40
     unlocking
    0.40
     werden
    0.39
    Activations Density 0.000%

    No Known Activations