© 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. 2768
    Prev
    Next
    INDEX
    Explanations

    movie listings and brainstorming

    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
    Coef
    0.90
     Nahin
    0.88
    sson
    0.86
    Hann
    0.86
    ALBERT
    0.86
    sail
    0.85
     OEMs
    0.85
    ̝
    0.85
    INN
    0.84
     Caed
    0.83
    POSITIVE LOGITS
     directory
    1.15
     commenting
    1.13
     demol
    1.13
     Comment
    1.12
    comment
    1.10
     Directory
    1.09
     Monument
    1.09
     Grandmother
    1.07
     Jolie
    1.07
     demolished
    1.05
    Activations Density 0.178%

    No Known Activations