© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8919
    Prev
    Next
    INDEX
    Explanations

    mentions of product features

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

    features

    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_40_width_16k_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
    etzung
    0.42
    TYPES
    0.42
     代
    0.40
     prejud
    0.40
    IDENTAL
    0.39
     מז
    0.39
    estries
    0.39
    ロス
    0.38
    Joining
    0.38
    苣
    0.38
    POSITIVE LOGITS
     features
    2.59
    features
    2.45
     feature
    2.39
     Features
    2.38
    feature
    2.31
    Features
    2.30
     FEATURES
    2.22
     fitur
    2.16
     Feature
    2.11
    FEATURES
    2.09
    Activations Density 0.463%

    No Known Activations