© 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. 176049
    Prev
    Next
    INDEX
    Explanations

    leading vocal, save a life, still laugh

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

    biosynthetic origin or pathways

    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
    reated
    0.42
    াক্তন
    0.41
    aker
    0.40
    tableau
    0.40
    itched
    0.40
    ापुर
    0.39
    folger
    0.39
    셨
    0.39
    手里
    0.39
    even
    0.38
    POSITIVE LOGITS
     covari
    0.52
     diph
    0.52
     offend
    0.49
     shabd
    0.49
     サ
    0.49
    ဝ
    0.47
     $"
    0.47
     গর
    0.46
     อ่ะ
    0.46
     circum
    0.46
    Activations Density 0.001%

    No Known Activations