© 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. 110774
    Prev
    Next
    INDEX
    Explanations

    used and refurbished items

    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
     intact
    0.49
     unused
    0.47
     undamaged
    0.45
     jarang
    0.45
     pristine
    0.43
     상태
    0.43
     unscathed
    0.42
    筮
    0.42
    未使用
    0.41
    unused
    0.40
    POSITIVE LOGITS
     refurbishment
    0.61
     refurb
    0.59
     refurbished
    0.58
     processed
    0.48
     proces
    0.47
     processing
    0.46
     செயல்
    0.45
    processed
    0.45
     віднов
    0.44
     renovated
    0.44
    Activations Density 0.006%

    No Known Activations