© 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. 245728
    Prev
    Next
    INDEX
    Explanations

    Interpreting photographer

    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
    ad
    0.47
     Brist
    0.45
    amano
    0.44
    %;
    0.43
    it
    0.42
    メイド
    0.42
    amélioration
    0.42
    市の
    0.42
    ん
    0.41
    пад
    0.41
    POSITIVE LOGITS
     Interpre
    0.50
     interpre
    0.48
     Umar
    0.46
     zuk
    0.46
    睽
    0.45
     Photographer
    0.45
     Puis
    0.44
     UserRepository
    0.44
     ANSWER
    0.43
     Aye
    0.43
    Activations Density 0.000%

    No Known Activations