© 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. 195842
    Prev
    Next
    INDEX
    Explanations

    conjunction with managers / children

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

    negation, assessment, pipe, potential

    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
    parsedBlock
    0.58
    ర్థిక
    0.55
     શહે
    0.55
     Ники
    0.54
    FURNIZOR
    0.53
     Ҳ
    0.52
     പഴ
    0.50
     控制
    0.50
    UIControlState
    0.50
     Hải
    0.49
    POSITIVE LOGITS
    iert
    0.43
     RE
    0.42
     arguments
    0.40
     ober
    0.40
     IRC
    0.40
     studies
    0.39
    stens
    0.39
     enduro
    0.39
     authentication
    0.39
     estruct
    0.39
    Activations Density 0.001%

    No Known Activations