© 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. 222114
    Prev
    Next
    INDEX
    Explanations

    relationships, family, and future topics

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

    progressing or asking questions sequentially

    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
    爣
    0.50
     然後
    0.49
     instantiation
    0.47
     掛
    0.46
     vértice
    0.46
    一個
    0.45
     वैसा
    0.45
    ホル
    0.44
     ತಿ
    0.44
     vuttam
    0.44
    POSITIVE LOGITS
    رش
    0.51
     قریب
    0.49
     to
    0.49
    تهم
    0.44
     decimal
    0.42
    圩
    0.42
     treas
    0.41
    ♪
    0.40
    荠
    0.40
     сбор
    0.40
    Activations Density 0.001%

    No Known Activations