© 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. 31-GEMMASCOPE-2-RES-65K
    7. 27353
    Prev
    Next
    INDEX
    Explanations

    parentheses followed by numbers

    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_31_width_65k_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
    齙
    0.47
    、
    0.41
     centerX
    0.40
     concatenated
    0.39
     granular
    0.38
     globules
    0.38
     generalizing
    0.38
     demethyl
    0.36
    вой
    0.35
     diluted
    0.35
    POSITIVE LOGITS
    ontiti
    0.42
     verfügt
    0.40
    a
    0.40
    '):
    0.40
    izi
    0.39
    authorize
    0.39
    entiti
    0.39
    ula
    0.38
     Waiver
    0.38
    ka
    0.38
    Activations Density 0.001%

    No Known Activations