© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 83225
    Prev
    Next
    INDEX
    Explanations

    adding small amounts

    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_53_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
     somehow
    0.44
     Somehow
    0.44
    Salt
    0.41
     Salt
    0.40
    spice
    0.40
     Somewhere
    0.40
    銨
    0.39
    Eggs
    0.39
    give
    0.38
    塩
    0.38
    POSITIVE LOGITS
     spoonful
    0.68
     немного
    0.61
    少量
    0.56
     थोड़ा
    0.55
     थोड़ी
    0.55
     mouthful
    0.53
     थोडे
    0.52
     थोड़ा
    0.52
     சிறி
    0.52
     biraz
    0.51
    Activations Density 0.024%

    No Known Activations