© 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. 69347
    Prev
    Next
    INDEX
    Explanations

    issue of

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

    asking about an issue

    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
    jší
    1.10
    tų
    1.05
    し
    1.04
    ться
    0.98
    town
    0.96
     hypothes
    0.91
    ని
    0.91
    toare
    0.89
    ti
    0.87
    ır
    0.86
    POSITIVE LOGITS
    س
    1.37
    0
    1.35
    v
    1.32
    h
    1.20
    al
    1.20
    Т
    1.20
    ING
    1.16
    ا
    1.16
    ع
    1.16
    of
    1.13
    Activations Density 0.040%

    No Known Activations