© 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-262K
    7. 57339
    Prev
    Next
    INDEX
    Explanations

    retries

    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_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
     antibiotic
    0.47
    ́
    0.47
     uphol
    0.46
     stomachs
    0.44
     floors
    0.42
     film
    0.42
     embro
    0.42
     become
    0.42
     appraised
    0.42
     scop
    0.41
    POSITIVE LOGITS
    ANG
    0.50
    ਊ
    0.45
    Alla
    0.44
    Neces
    0.44
    АН
    0.44
    4
    0.44
    ാനാ
    0.43
    Brasil
    0.43
    咩
    0.43
    耒
    0.42
    Activations Density 0.005%

    No Known Activations