© 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. 187533
    Prev
    Next
    INDEX
    Explanations

    where communities

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

    colon, equals, markdown emphasis

    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
     Sebelum
    0.51
     Suggestions
    0.45
     Ergebnisse
    0.44
     Beispiele
    0.43
    మన్
    0.43
     Aplikasi
    0.43
    魟
    0.42
    மன்
    0.42
     olmak
    0.42
    琹
    0.42
    POSITIVE LOGITS
    avoid
    0.51
    assert
    0.50
    }
    0.50
    defined
    0.49
    svelte
    0.48
    detection
    0.46
    azd
    0.46
    assertEqual
    0.45
    approximately
    0.45
     singularities
    0.45
    Activations Density 0.000%

    No Known Activations