© 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. 100447
    Prev
    Next
    INDEX
    Explanations

    Mari Marian EXO OSU

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

    product of zero

    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
    }$,
    0.58
     nedenle
    0.51
    }$
    0.48
     inkább
    0.48
    }=
    0.46
    förm
    0.46
    });
    0.46
    </strong>
    0.45
    sempel
    0.45
     mercados
    0.44
    POSITIVE LOGITS
     Painted
    0.50
     Panoramic
    0.48
     Mari
    0.47
     Marian
    0.47
    Mari
    0.46
     Futuristic
    0.46
    廷
    0.45
     Рассмотрим
    0.44
     EXO
    0.43
     OSU
    0.43
    Activations Density 0.001%

    No Known Activations