© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 81099
    Prev
    Next
    INDEX
    Explanations

    engineering, enterprise, entity, efficient learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enció
    0.42
    $};
    0.40
    𓍊
    0.39
    ㈣
    0.38
    ease
    0.38
    ustration
    0.38
    ющее
    0.37
    oinette
    0.37
     fortemente
    0.37
    }');
    0.37
    POSITIVE LOGITS
     LE
    0.70
     HE
    0.70
     JE
    0.67
     BE
    0.65
    HE
    0.64
     ZE
    0.63
     PE
    0.62
     KE
    0.61
     TE
    0.59
     ME
    0.55
    Activations Density 0.025%

    No Known Activations