© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28453
    Prev
    Next
    INDEX
    Explanations

    account credentials and devices

    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
     detonation
    0.47
     delinqu
    0.46
    <unused60>
    0.45
     molecular
    0.42
     concatenated
    0.41
     degeneracy
    0.41
     perturbations
    0.40
     unsolved
    0.40
     reforms
    0.40
     decryption
    0.39
    POSITIVE LOGITS
     Ко
    0.54
    ®.
    0.51
     पाण्या
    0.48
     Само
    0.46
     ശരീര
    0.46
    äle
    0.45
     للص
    0.44
     вод
    0.44
     والأ
    0.44
     كيفية
    0.44
    Activations Density 0.015%

    No Known Activations