© 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. 136416
    Prev
    Next
    INDEX
    Explanations

    states specific situations

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

    organizing content and actions

    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
    乓
    0.48
    隨著
    0.43
    ン
    0.42
    ሔ
    0.41
    לק
    0.41
    밟
    0.41
    ធ្វ
    0.40
    హ
    0.40
     selectTable
    0.40
    振動
    0.40
    POSITIVE LOGITS
     Karlsruhe
    0.49
     Cosmetic
    0.49
     cosmetic
    0.48
     চেহারা
    0.46
     Editions
    0.45
    droid
    0.45
    extensions
    0.44
    chia
    0.44
    भीत
    0.43
     Darmstadt
    0.43
    Activations Density 0.000%

    No Known Activations