© 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. 5170
    Prev
    Next
    INDEX
    Explanations

    calculate quantities

    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
    hened
    0.47
    き
    0.47
     Kön
    0.45
    agland
    0.42
     Pemer
    0.41
     *)$
    0.41
     одну
    0.40
     Hadd
    0.40
    aking
    0.40
    ests
    0.40
    POSITIVE LOGITS
    評價
    0.48
    。」
    0.46
     hobbies
    0.44
    ፑ
    0.41
     sorgen
    0.40
    বা
    0.40
    澼
    0.40
     financi
    0.39
    బ్బు
    0.39
    арма
    0.39
    Activations Density 0.001%

    No Known Activations