© 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. 115451
    Prev
    Next
    INDEX
    Explanations

    users active

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

    identifying entities followed by descriptions

    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
    }/>
    0.52
    ش
    0.48
    ש
    0.47
    channel
    0.47
    Fate
    0.46
    Rajas
    0.45
    shakes
    0.45
    ذ
    0.44
     executes
    0.44
    𝙙
    0.43
    POSITIVE LOGITS
    are
    0.50
     μεταξύ
    0.50
    ie
    0.48
     හා
    0.46
     स्टैंडर्ड
    0.46
     giỏi
    0.46
    μενο
    0.46
    assertArg
    0.45
    ート
    0.45
     説明
    0.45
    Activations Density 0.000%

    No Known Activations