© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47181
    Prev
    Next
    INDEX
    Explanations

    time and quantities

    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_31_width_65k_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
     feld
    0.46
    먀
    0.44
     вино
    0.44
    ทีม
    0.43
     kuru
    0.43
     racking
    0.42
     Leader
    0.42
     dabb
    0.42
     rave
    0.41
    <unused2187>
    0.41
    POSITIVE LOGITS
    '}
    0.46
    '})
    0.44
    ung
    0.43
    новения
    0.42
    spre
    0.41
    ord
    0.41
    ibilit
    0.41
    ರುತ್ತ
    0.41
    MeToo
    0.41
    CLUDES
    0.40
    Activations Density 0.017%

    No Known Activations