© 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. 40-GEMMASCOPE-2-RES-262K
    7. 16246
    Prev
    Next
    INDEX
    Explanations

    counters and Espresso

    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_40_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
    瀵
    0.45
    Sliders
    0.38
     символ
    0.37
    test
    0.37
     切
    0.35
     симво
    0.35
    вис
    0.35
    ᔭ
    0.35
     parag
    0.35
    ò
    0.34
    POSITIVE LOGITS
     thinly
    0.45
     Counting
    0.43
    antoor
    0.43
     expeditions
    0.42
    Counting
    0.42
     idling
    0.42
     boldly
    0.41
     absorption
    0.41
     infusions
    0.41
    fangs
    0.41
    Activations Density 0.000%

    No Known Activations