© 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. 112235
    Prev
    Next
    INDEX
    Explanations

    Mutation Profiles, warm water, Digital Foundry, I shall

    np_acts-logits-general · gemini-2.5-flash-lite

    contrasting different things

    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
     incumbent
    0.49
    amız
    0.47
     seller
    0.46
    饲
    0.45
    aksi
    0.42
    лист
    0.42
     조직
    0.42
    сколько
    0.40
    ouser
    0.40
     俺
    0.40
    POSITIVE LOGITS
     จน
    0.53
     disparition
    0.51
     येतात
    0.51
     nejsou
    0.46
     llegan
    0.46
    不斷
    0.45
     идут
    0.44
    各式
    0.44
    vanishing
    0.43
     desapare
    0.43
    Activations Density 0.001%

    No Known Activations