© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4161
    Prev
    Next
    INDEX
    Explanations

    what happens next

    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
     with
    1.50
     visited
    1.45
     of
    1.44
     announced
    1.42
    により
    1.38
     enjoyed
    1.37
     brachte
    1.36
    ,:
    1.32
     của
    1.29
     timeline
    1.27
    POSITIVE LOGITS
    Additionally
    2.41
    Corresponding
    2.39
    Furthermore
    2.33
     Furthermore
    2.32
    Consent
    2.31
     Additionally
    2.30
    However
    2.23
    Entities
    2.22
    Each
    2.19
    Moreover
    2.16
    Activations Density 0.050%

    No Known Activations