© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91407
    Prev
    Next
    INDEX
    Explanations

    finding or being

    np_acts-logits-general · gemini-2.5-flash-lite

    actions after "turn"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    7
    0.52
    3
    0.44
    5
    0.43
    6
    0.43
    8
    0.42
     Biraz
    0.41
    𝙰
    0.41
    手的
    0.40
    9
    0.40
     INDUSTRIES
    0.39
    POSITIVE LOGITS
     detract
    0.43
     forl
    0.42
     avoidable
    0.38
     pathways
    0.38
     grossly
    0.38
    Paths
    0.36
     carbonic
    0.36
     zapewn
    0.36
     horr
    0.36
     defin
    0.36
    Activations Density 0.002%

    No Known Activations