© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90894
    Prev
    Next
    INDEX
    Explanations

    specific words / punctuation

    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
    々
    0.47
    Favourites
    0.45
    Direction
    0.43
     บริษัท
    0.43
    తె
    0.43
     allow
    0.42
    Allow
    0.42
    Favorites
    0.42
    警
    0.42
     warn
    0.42
    POSITIVE LOGITS
     extracción
    0.49
     protección
    0.46
     tệ
    0.46
     permangan
    0.44
     хло
    0.42
     hapl
    0.42
     мере
    0.41
    hutang
    0.41
     Kaya
    0.41
     esposo
    0.41
    Activations Density 0.005%

    No Known Activations