© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52018
    Prev
    Next
    INDEX
    Explanations

    pooling and normalization

    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
    Rain
    0.47
    rainfall
    0.45
    о
    0.45
     inoxid
    0.45
     rains
    0.44
    а
    0.43
    チャンピオン
    0.42
     علیہ
    0.42
     rainfall
    0.40
    launch
    0.40
    POSITIVE LOGITS
     tathapi
    0.45
     llevaba
    0.45
     بير
    0.44
    मधील
    0.43
    比起
    0.43
    wau
    0.42
    ról
    0.42
    ేష్
    0.42
     เตรียม
    0.42
    ᒎ
    0.41
    Activations Density 0.002%

    No Known Activations