© 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. 426
    Prev
    Next
    INDEX
    Explanations

    English locations and terms

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

    command structure

    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
     проє
    0.45
     біль
    0.44
    <unused1059>
    0.43
    <unused1008>
    0.42
    🫶
    0.42
    ꧁
    0.42
    <unused1073>
    0.41
     שלנו
    0.40
    🫣
    0.40
    🤫
    0.40
    POSITIVE LOGITS
     I
    0.48
    0.46
     UK
    0.45
     Clip
    0.42
     be
    0.42
     to
    0.41
     L
    0.41
     centre
    0.41
     depots
    0.41
     centres
    0.40
    Activations Density 0.101%

    No Known Activations