© 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-65K
    7. 914
    Prev
    Next
    INDEX
    Explanations

    broken into pieces or chunks

    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_65k_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
    핼
    0.43
     sourceType
    0.42
    軹
    0.36
     काली
    0.35
    娶
    0.35
     যাবতীয়
    0.35
    ammable
    0.35
    罟
    0.34
     sanction
    0.34
    boBox
    0.34
    POSITIVE LOGITS
     fragments
    2.52
     fragment
    2.34
    fragments
    2.23
    fragment
    2.19
     Fragment
    2.16
     fragmented
    2.16
     Fragments
    2.16
    Fragment
    2.11
     fragmentation
    2.09
    Fragments
    2.09
    Activations Density 0.221%

    No Known Activations