© 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. 110513
    Prev
    Next
    INDEX
    Explanations

    Roots revenge

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

    movie titles mixed with visual terms

    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
    у
    0.50
    his
    0.46
     Kurt
    0.46
     mostly
    0.44
     graciously
    0.43
    relative
    0.43
     In
    0.42
    е
    0.41
    and
    0.41
     Min
    0.41
    POSITIVE LOGITS
     अपहरण
    0.54
     antérieure
    0.52
     प्रकर
    0.52
     leyes
    0.51
     connaissance
    0.51
     asesin
    0.51
     princípios
    0.50
     downregulation
    0.50
     unlaw
    0.50
     transgression
    0.50
    Activations Density 0.001%

    No Known Activations