© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1206
    Prev
    Next
    INDEX
    Explanations

    LaTeX, £, cheque

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    8
    1.81
    7
    1.72
    6
    1.59
    atributo
    1.41
    3
    1.40
     ozone
    1.39
    ohr
    1.39
     mesenchymal
    1.37
    9
    1.34
     Omb
    1.33
    POSITIVE LOGITS
    LaTeX
    1.45
    pex
    1.44
     (£
    1.44
    tex
    1.39
    tee
    1.33
     Tipp
    1.30
     Plas
    1.27
    TeX
    1.25
     cheque
    1.25
     LaTeX
    1.23
    Activations Density 0.026%

    No Known Activations