© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 137263
    Prev
    Next
    INDEX
    Explanations

    recognizing diverse concepts

    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_40_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
     homeowners
    0.44
     callbacks
    0.41
     montagnes
    0.41
    쩔
    0.41
    筊
    0.40
     يتيمه
    0.40
     billionaires
    0.39
     scammers
    0.39
     boulders
    0.39
     transducers
    0.38
    POSITIVE LOGITS
    oton
    0.43
     डिस्क
    0.40
     beforeDir
    0.40
     condição
    0.39
     diện
    0.39
    зон
    0.39
     रेडियो
    0.38
     хро
    0.38
     Europa
    0.38
    Ꮬ
    0.38
    Activations Density 0.000%

    No Known Activations