© 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. 28950
    Prev
    Next
    INDEX
    Explanations

    common words followed by common connectors

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

    setting goals or ideas

    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
    é
    0.46
    lo
    0.45
     frantic
    0.45
    usus
    0.42
     minus
    0.42
    ino
    0.42
     Mald
    0.42
     poncho
    0.41
    o
    0.41
    EDS
    0.40
    POSITIVE LOGITS
     einzel
    0.53
    segaretro
    0.52
    を備
    0.51
    studentRecord
    0.50
    াবদ্ধ
    0.50
    ንዳንድ
    0.50
     Achievements
    0.49
    🏏
    0.49
    দেব
    0.48
    することができる
    0.48
    Activations Density 0.000%

    No Known Activations