© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 16497
    Prev
    Next
    INDEX
    Explanations

    cry of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    1.59
     (
    1.41
    ன்
    1.40
    ור
    1.25
    ’
    1.13
    س
    1.10
    с
    1.05
    मध्ये
    1.03
     tassels
    1.02
    ور
    1.02
    POSITIVE LOGITS
    9
    1.52
    3
    1.25
    2
    1.23
    1
    1.20
    8
    1.20
     I
    1.15
    7
    1.15
    cry
    1.14
    I
    1.13
     not
    1.00
    Activations Density 0.003%

    No Known Activations