© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 242154
    Prev
    Next
    INDEX
    Explanations

    Turn on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    麺
    0.48
    OFFSET
    0.41
    最小
    0.41
    esterol
    0.40
    まり
    0.40
    スペシャル
    0.40
    曽
    0.39
     donated
    0.39
     названия
    0.38
     দল
    0.38
    POSITIVE LOGITS
     apparaît
    0.51
     acrob
    0.48
     appara
    0.47
     seno
    0.45
     upaya
    0.43
     الاك
    0.43
    akha
    0.42
    詓
    0.42
    odha
    0.42
     lmao
    0.42
    Activations Density 0.004%

    No Known Activations