© 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. 165033
    Prev
    Next
    INDEX
    Explanations

    preliminary appointment

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

    mother, models, separately

    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
     Continuando
    0.47
     لط
    0.45
     روان
    0.45
    posaż
    0.43
     Enrollment
    0.42
     Violence
    0.42
    綽
    0.41
    ष्णु
    0.41
     خلال
    0.41
    来说
    0.41
    POSITIVE LOGITS
     {};
    0.54
     precluded
    0.49
    al
    0.49
    az
    0.49
    av
    0.48
     superimposed
    0.47
     reserved
    0.47
     resonance
    0.47
    ಿಕೆಯ
    0.47
    که
    0.46
    Activations Density 0.000%

    No Known Activations