© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 29309
    Prev
    Next
    INDEX
    Explanations

    navigational and meta terms

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

    URLs and resource links

    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
    alu
    0.40
     گل
    0.38
    ما
    0.36
    PrivateRoute
    0.35
    drž
    0.35
    δ
    0.35
    spam
    0.35
    αν
    0.34
    ቦች
    0.33
    alik
    0.33
    POSITIVE LOGITS
    তামূলক
    0.40
    藹
    0.40
    ﻯ
    0.40
    یت
    0.39
    ನೆಯ
    0.39
    暘
    0.39
     amal
    0.39
    ificio
    0.39
     suced
    0.38
     বিশেষভাবে
    0.38
    Activations Density 0.041%

    No Known Activations