© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2643
    Prev
    Next
    INDEX
    Explanations

    lists or bullet points

    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
     wyn
    1.17
     швидко
    1.13
     spermato
    1.13
     pathologists
    1.13
     veloc
    1.12
     Тар
    1.10
    簽
    1.10
     personalizado
    1.06
     residents
    1.06
     Марина
    1.05
    POSITIVE LOGITS
     B
    1.46
    B
    1.45
    A
    1.45
     A
    1.42
    C
    1.24
     C
    1.22
     Bs
    0.91
     D
    0.90
    Bm
    0.87
    D
    0.85
    Activations Density 0.289%

    No Known Activations