© 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. 123215
    Prev
    Next
    INDEX
    Explanations

    customer service and ordering

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

    Key Considerations

    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
    Arrows
    0.44
    orragie
    0.43
    起到
    0.42
     організації
    0.42
    ёшь
    0.41
    stärke
    0.41
    უნქ
    0.41
    🕘
    0.39
    🥜
    0.39
    🗼
    0.39
    POSITIVE LOGITS
     best
    0.43
     BEST
    0.41
     Best
    0.40
    テー
    0.39
     testimonials
    0.38
     օ
    0.38
    ड
    0.38
    個セット
    0.38
     whistleblower
    0.37
    โปร
    0.37
    Activations Density 0.001%

    No Known Activations