© 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. 4180
    Prev
    Next
    INDEX
    Explanations

    function takes

    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
     zeroth
    0.97
     aliphatic
    0.95
     elects
    0.94
    aund
    0.94
    anediyl
    0.92
    ziest
    0.90
    blower
    0.89
    琦
    0.89
    érieurs
    0.88
    ynit
    0.87
    POSITIVE LOGITS
     Nu
    1.60
     Location
    1.53
     Ac
    1.52
     Tre
    1.48
     Price
    1.48
     Architecture
    1.47
     Tra
    1.46
     Network
    1.46
     Sharing
    1.44
     Court
    1.42
    Activations Density 0.006%

    No Known Activations