© 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. 155243
    Prev
    Next
    INDEX
    Explanations

    his deceased family members

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

    deaths of family and successors

    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
    䄸
    0.41
     cotidian
    0.39
     separations
    0.38
    ysseus
    0.38
    ukhov
    0.38
     reconnection
    0.38
    秚
    0.37
    ሳ
    0.37
     coping
    0.37
    rakech
    0.37
    POSITIVE LOGITS
     jego
    0.73
     его
    0.71
     his
    0.68
     його
    0.68
    彼の
    0.67
    他的
    0.66
     그의
    0.66
     त्याच्या
    0.65
     njegove
    0.65
    his
    0.65
    Activations Density 0.044%

    No Known Activations