© 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. 4120
    Prev
    Next
    INDEX
    Explanations

    The Theory

    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
     ocul
    0.87
     newspap
    0.82
     deleteTask
    0.82
    投
    0.81
     moneys
    0.80
     $=$
    0.80
     hypnot
    0.79
    Panning
    0.78
     taskId
    0.78
    hline
    0.78
    POSITIVE LOGITS
    6
    3.12
    7
    3.12
    3
    3.09
    4
    3.07
    8
    3.05
    5
    2.88
    2
    2.86
    9
    2.78
    0
    2.63
    1
    2.56
    Activations Density 0.096%

    No Known Activations