© 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-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240510
    Prev
    Next
    INDEX
    Explanations

    Jesus Christ titles relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_width_262k_l0_small_affine
    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
     affinities
    0.37
    ulfillment
    0.36
     util
    0.36
     utilities
    0.35
    식
    0.34
     وو
    0.33
    Template
    0.32
    Edges
    0.32
    能在
    0.32
     보
    0.31
    POSITIVE LOGITS
     परसेंट
    0.42
    abria
    0.42
     familias
    0.42
    ாதி
    0.41
    আপনি
    0.41
     Catawiki
    0.40
     maravill
    0.39
    உலகின்
    0.38
     Rusland
    0.38
     auctor
    0.38
    Activations Density 0.000%

    No Known Activations