© 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. 2918
    Prev
    Next
    INDEX
    Explanations

    explaining or justifying actions

    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
    6
    1.24
    lica
    1.11
    4
    1.08
    7
    1.07
     Greensboro
    1.07
    º
    1.01
     Apparel
    1.01
    3
    0.97
     Collection
    0.97
     Memphis
    0.97
    POSITIVE LOGITS
     explanations
    1.42
     explanation
    1.31
     mata
    1.30
     explains
    1.29
     عين
    1.29
     evidence
    1.28
     entrambi
    1.27
     deliberations
    1.26
     both
    1.24
     explaining
    1.20
    Activations Density 0.059%

    No Known Activations