© 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. 203646
    Prev
    Next
    INDEX
    Explanations

    Learn how to

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

    explaining step-by-step

    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
     rechts
    0.48
    file
    0.46
    frage
    0.45
     exchange
    0.45
     salvation
    0.44
    يق
    0.42
     Buchstaben
    0.42
    誓
    0.42
     homomorphism
    0.42
     salvage
    0.42
    POSITIVE LOGITS
    IDENTITY
    0.51
     analisar
    0.50
    ເປັນ
    0.49
     tạp
    0.47
    HAD
    0.46
    ihad
    0.45
     traveling
    0.45
    ாயம்
    0.44
    ttf
    0.43
     টে
    0.43
    Activations Density 0.000%

    No Known Activations