© 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. 53205
    Prev
    Next
    INDEX
    Explanations

    special characters and words

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

    "` `. `)` `searches` `marks`

    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
    ם
    0.55
    ।
    0.48
    ן
    0.46
    ubmit
    0.46
    ным
    0.46
    🚢
    0.45
    箐
    0.45
    শিশ
    0.44
     decisive
    0.43
    🏝
    0.43
    POSITIVE LOGITS
    ელია
    0.44
    硫酸
    0.42
     Tug
    0.42
    JZ
    0.41
     ਕਰ
    0.40
     波
    0.40
     Lately
    0.40
     دارد
    0.39
     لون
    0.39
     三角
    0.39
    Activations Density 0.000%

    No Known Activations