© 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. 19770
    Prev
    Next
    INDEX
    Explanations

    don't worry if

    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
     za
    0.47
     pon
    0.47
     inz
    0.44
    <unused62>
    0.44
     lors
    0.44
    }'],
    0.43
     lauf
    0.43
     attenuation
    0.42
     SCALE
    0.42
     Antony
    0.42
    POSITIVE LOGITS
    softmax
    0.48
    same
    0.43
    a
    0.43
    astar
    0.43
     بہتر
    0.43
    uncertain
    0.42
    naires
    0.42
    रात
    0.41
    mobility
    0.41
    ech
    0.41
    Activations Density 0.001%

    No Known Activations