© 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. 142957
    Prev
    Next
    INDEX
    Explanations

    home consumption, final decision, Express technology

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

    structured lists or code blocks

    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
     declara
    0.55
    鸷
    0.54
     zwięks
    0.54
     accél
    0.53
     declarar
    0.52
     întâ
    0.52
     déclar
    0.49
     ذکر
    0.48
     declar
    0.48
     poveć
    0.48
    POSITIVE LOGITS
    Anyway
    0.43
    RP
    0.42
     ProductCategory
    0.40
    ស
    0.40
    rón
    0.40
    Formula
    0.39
    ណ្ឌ
    0.39
    Helper
    0.38
    Incidentally
    0.38
    uable
    0.38
    Activations Density 0.001%

    No Known Activations