© 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. 237188
    Prev
    Next
    INDEX
    Explanations

    month and day

    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
    }=(
    0.59
    嗶
    0.54
     ಗಾ
    0.53
    lastval
    0.48
     vidhan
    0.48
     rač
    0.48
     orthon
    0.47
    }^{(\
    0.47
     stojí
    0.47
    }=(\
    0.47
    POSITIVE LOGITS
     divisional
    0.48
    1
    0.44
     one
    0.44
     molecular
    0.43
     Dong
    0.43
     dean
    0.43
     Fitzgerald
    0.43
    Winter
    0.43
     Dawn
    0.42
     dawn
    0.42
    Activations Density 0.000%

    No Known Activations