© 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. 132895
    Prev
    Next
    INDEX
    Explanations

    disability and misconception

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

    range of

    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
    ünk
    0.49
     lửa
    0.49
     والے
    0.46
     eaux
    0.45
     vải
    0.45
    용
    0.44
    वार
    0.44
     vocals
    0.44
    ቦች
    0.44
     गाडी
    0.43
    POSITIVE LOGITS
     CHANG
    0.56
     DISABLED
    0.48
     Provinc
    0.47
    ETIC
    0.47
    CHANGED
    0.46
     terug
    0.46
     أَ
    0.46
     prioridad
    0.46
    ➛
    0.46
    CLUDING
    0.46
    Activations Density 0.001%

    No Known Activations