© 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. 28210
    Prev
    Next
    INDEX
    Explanations

    spirit of

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

    vibe check

    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
    ina
    0.67
    ene
    0.64
    ao
    0.58
    ı
    0.57
    ie
    0.57
    age
    0.55
    ane
    0.55
    eda
    0.54
    your
    0.54
    í
    0.53
    POSITIVE LOGITS
     분위
    1.33
     атмос
    1.20
    雰囲気
    1.18
    气氛
    1.16
     atmosfera
    1.14
    氛
    1.13
     atmosphere
    1.10
     atmospheres
    1.07
    雰囲
    1.05
     esprit
    1.05
    Activations Density 0.068%

    No Known Activations