© 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. 137774
    Prev
    Next
    INDEX
    Explanations

    links again or back

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

    list item properties

    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
     பகிர்ந்து
    0.54
    டுகிறது
    0.51
    टेज
    0.50
    等等
    0.49
    紥
    0.49
    口罩
    0.47
    zonego
    0.47
     конденса
    0.46
     ஆ
    0.46
     vuccanti
    0.46
    POSITIVE LOGITS
    ここ
    0.52
     clic
    0.52
     Real
    0.50
    Cairo
    0.48
     César
    0.48
    0
    0.47
     pointe
    0.47
    Founded
    0.46
     headquarters
    0.46
    José
    0.46
    Activations Density 0.002%

    No Known Activations