© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 204460
    Prev
    Next
    INDEX
    Explanations

    classification and transcription

    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
     Politiker
    0.41
     ಸರ್ಕಾರದ
    0.38
    焘
    0.36
     डायरे
    0.36
    扮
    0.36
    络
    0.36
     administrador
    0.35
     मुखिया
    0.35
    乔
    0.35
    㖮
    0.35
    POSITIVE LOGITS
     POM
    0.44
     continents
    0.42
     transcription
    0.41
     Transcript
    0.39
     sklad
    0.38
    transcript
    0.38
     sludge
    0.37
     raíces
    0.37
    classification
    0.37
     clones
    0.37
    Activations Density 0.002%

    No Known Activations