© 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. 8453
    Prev
    Next
    INDEX
    Explanations

    actions with consequences

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

    providing context or explanation

    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
    ®.
    0.38
     کی۔
    0.37
    ™.
    0.37
     koriste
    0.35
     ہوا۔
    0.34
    *.
    0.34
    ',
    0.33
    .*
    0.32
    °.
    0.32
    _.
    0.31
    POSITIVE LOGITS
    というのは
    0.44
    ிருப்பது
    0.42
     is
    0.40
     είναι
    0.40
    ということは
    0.39
     является
    0.38
     zorgt
    0.38
     bedeutet
    0.36
     znamená
    0.36
    한다는
    0.36
    Activations Density 0.599%

    No Known Activations