© 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. 197632
    Prev
    Next
    INDEX
    Explanations

    from the beginning

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

    conveying nuance or qualification

    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
     Enough
    0.48
    சை
    0.46
    髒
    0.46
    <h1>
    0.46
    Debug
    0.46
    鈈
    0.46
     Drink
    0.45
    ibilité
    0.44
    洳
    0.44
    Drink
    0.43
    POSITIVE LOGITS
     postpone
    0.49
     consequent
    0.48
     preconceived
    0.48
     truthful
    0.48
     concurred
    0.45
     prerogative
    0.44
    inception
    0.44
     vehement
    0.44
     premio
    0.43
     initio
    0.43
    Activations Density 0.002%

    No Known Activations