© 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. 175807
    Prev
    Next
    INDEX
    Explanations

    worlds information

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

    explaining breakdowns and limitations

    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
    InitStruct
    0.44
     unify
    0.44
     triun
    0.44
     tea
    0.43
     hashMap
    0.43
    卉
    0.43
     poppy
    0.42
     unilateral
    0.42
     waterway
    0.42
    HY
    0.42
    POSITIVE LOGITS
    custList
    0.53
    ihat
    0.49
    ရ
    0.48
     सकाळी
    0.47
    frak
    0.47
    மில்லை
    0.45
     sebagaimana
    0.45
     रात्री
    0.45
     অংশে
    0.45
     มาก
    0.43
    Activations Density 0.000%

    No Known Activations