© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46798
    Prev
    Next
    INDEX
    Explanations

    identify gaps and results

    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_31_width_65k_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
    rą
    0.47
    ńsk
    0.44
    悹
    0.43
    īg
    0.43
     gavel
    0.39
     వచ్చింది
    0.38
     Frye
    0.38
     orifice
    0.38
    unek
    0.38
    最好
    0.38
    POSITIVE LOGITS
    レ
    0.47
    ла
    0.46
    𝘃
    0.44
     vx
    0.43
     produzir
    0.42
     estejam
    0.41
     putern
    0.41
    leh
    0.41
    ل
    0.41
     autón
    0.41
    Activations Density 0.003%

    No Known Activations