© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 226688
    Prev
    Next
    INDEX
    Explanations

    city rooftop/me/voice of/most/packaging/appreciated/experience./hubcaps

    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
    Negative Logits
    ன்
    0.49
    فع
    0.42
    ਲ
    0.42
    ကျ
    0.41
    ール
    0.39
    oliberal
    0.39
    र्व
    0.38
    ewidth
    0.38
    circled
    0.38
     billion
    0.37
    POSITIVE LOGITS
     busc
    0.50
    Só
    0.46
     одну
    0.46
    étr
    0.45
     постара
    0.45
     })();
    0.45
    Ét
    0.44
    五个
    0.43
     brauch
    0.43
    ěk
    0.43
    Activations Density 0.000%

    No Known Activations