© 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. 39848
    Prev
    Next
    INDEX
    Explanations

    required by, reports on

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

    redemption arcs, affects, flatter, visitors

    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
     minuten
    0.50
     uważ
    0.49
     Auswahl
    0.49
     importants
    0.46
     totalidad
    0.46
     selezion
    0.45
     sele
    0.45
    选
    0.45
     chọn
    0.44
     sélection
    0.44
    POSITIVE LOGITS
    ility
    0.52
    isa
    0.50
    ell
    0.48
    ISA
    0.46
    idden
    0.44
     /
    0.43
    dimethyl
    0.43
    icole
    0.43
    ͎
    0.42
    type
    0.42
    Activations Density 0.000%

    No Known Activations