© 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. 79242
    Prev
    Next
    INDEX
    Explanations

    specific terms and descriptions

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

    programming, security, and finance

    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
     અથવા
    0.52
     அல்லது
    0.49
     例えば
    0.48
    하거나
    0.47
     ಅಥವಾ
    0.46
     เช่น
    0.44
    などが
    0.44
     ἢ
    0.43
    その他の
    0.43
     または
    0.42
    POSITIVE LOGITS
     tuvimos
    0.41
     hubo
    0.40
     was
    0.39
     teve
    0.38
     took
    0.38
     salió
    0.38
     tellement
    0.37
     ook
    0.37
     ogrom
    0.37
     unsere
    0.36
    Activations Density 0.012%

    No Known Activations