© 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. 40-GEMMASCOPE-2-RES-262K
    7. 169586
    Prev
    Next
    INDEX
    Explanations

    photography, photographs, cameras

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    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
    }}^{*
    0.43
    IsEnabled
    0.42
    なくても
    0.40
    accès
    0.39
    Initialize
    0.39
     немає
    0.39
    বৃ
    0.39
    ไม่มี
    0.38
    ｇ
    0.38
    pyrrolo
    0.38
    POSITIVE LOGITS
     fotograf
    0.44
     photography
    0.43
     photographs
    0.43
     photographing
    0.43
     photograph
    0.43
     Covent
    0.42
     fotografie
    0.42
     Ration
    0.41
     Napoleon
    0.41
     storytelling
    0.40
    Activations Density 0.007%

    No Known Activations