© 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. 80657
    Prev
    Next
    INDEX
    Explanations

    specific descriptive terms

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

    demonstrate, needs, host, safety, applying, joints

    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
     casks
    0.53
     streamlining
    0.52
    }/>
    0.48
     validations
    0.47
     sheeting
    0.46
     plasmids
    0.46
     bales
    0.45
     complying
    0.45
    {-
    0.45
     convictions
    0.45
    POSITIVE LOGITS
     Bürger
    0.53
    ídas
    0.51
     Bauern
    0.50
    aktu
    0.47
    侑
    0.47
    琰
    0.46
    迩
    0.46
    ഞ്ഞി
    0.46
    ższy
    0.46
     Boundaries
    0.45
    Activations Density 0.001%

    No Known Activations