© 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. 117003
    Prev
    Next
    INDEX
    Explanations

    summer dates and pricing

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

    emphasis or affirmation

    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
     thiab
    0.50
    வ
    0.48
    vá
    0.48
     reread
    0.47
    2
    0.47
    와
    0.47
    ్ర
    0.47
    platz
    0.47
    と
    0.45
    ributions
    0.45
    POSITIVE LOGITS
     قبضہ
    0.65
     Charity
    0.47
    求め
    0.46
     Major
    0.46
     طریقہ
    0.45
     فائدہ
    0.45
     Covenant
    0.45
     Roque
    0.45
     Value
    0.44
     Blom
    0.44
    Activations Density 0.001%

    No Known Activations