© 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. 243338
    Prev
    Next
    INDEX
    Explanations

    bluegrass

    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
    <0xAC>
    0.53
     मुताब
    0.47
    <0xB3>
    0.44
    সল
    0.43
    WITH
    0.43
    ACTIV
    0.42
    Java
    0.41
     sock
    0.41
     TRANSM
    0.41
     terrorism
    0.41
    POSITIVE LOGITS
    isRequired
    0.55
     Vestone
    0.54
     Kamane
    0.52
    كز
    0.52
    ാരോഗ്യ
    0.51
     بیوی
    0.50
     Kiran
    0.49
    焯
    0.49
     അള
    0.49
    uo
    0.49
    Activations Density 0.001%

    No Known Activations