© 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. 15798
    Prev
    Next
    INDEX
    Explanations

    noun followed by modifier/preposition

    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
    Config
    0.38
    T
    0.37
    In
    0.36
     Config
    0.35
    ES
    0.35
    User
    0.33
    rav
    0.31
    AT
    0.31
    TO
    0.31
    config
    0.30
    POSITIVE LOGITS
    ୪
    0.38
     hoher
    0.37
    Ꮰ
    0.37
    性和
    0.35
     tightness
    0.35
    性と
    0.35
     infar
    0.35
    ously
    0.34
    stantial
    0.33
     deficits
    0.33
    Activations Density 0.052%

    No Known Activations