© 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. 4510
    Prev
    Next
    INDEX
    Explanations

    making story plots

    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
    garten
    1.06
    platinum
    1.05
    brä
    0.98
     uu
    0.98
    essen
    0.96
    fragen
    0.95
    werpen
    0.95
     "{{
    0.91
    azine
    0.91
    platin
    0.91
    POSITIVE LOGITS
     made
    2.31
     MADE
    2.19
    made
    2.16
    Made
    2.09
     Made
    2.04
     feitos
    2.00
    Making
    1.97
    MADE
    1.94
     feitas
    1.90
     Making
    1.88
    Activations Density 0.443%

    No Known Activations