© 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. 1702
    Prev
    Next
    INDEX
    Explanations

    asking for context

    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
     entour
    0.45
     rails
    0.44
    蝉
    0.43
     edu
    0.43
    羡慕
    0.43
    S
    0.43
     happenings
    0.42
    Ꭱ
    0.42
    லைப்
    0.42
    শীর
    0.41
    POSITIVE LOGITS
    anova
    0.51
     fabricante
    0.50
     zásobníku
    0.50
     nakon
    0.49
     domicilio
    0.48
    posição
    0.47
    alumno
    0.46
     després
    0.46
    repeated
    0.46
    Становништво
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.