© 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. 148188
    Prev
    Next
    INDEX
    Explanations

    sequences followed by common conjunctions

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

    conversational ai models and usage

    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
     Oakley
    0.50
     Taxation
    0.49
    ებში
    0.47
     Creating
    0.46
     создал
    0.45
     💕
    0.44
    gypte
    0.44
    களில்
    0.44
     समृद्ध
    0.43
    ম্ভ
    0.43
    POSITIVE LOGITS
     bip
    0.45
    اور
    0.44
    独自の
    0.44
    (
    0.43
    am
    0.43
     arh
    0.42
    絨
    0.42
    ्व
    0.42
     swe
    0.41
     ground
    0.40
    Activations Density 0.000%

    No Known Activations