© 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. 16-GEMMASCOPE-2-RES-262K
    7. 109288
    Prev
    Next
    INDEX
    Explanations

    decomposition, tight, type, truncation

    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_16_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
     spalle
    0.53
    Hö
    0.44
    Flare
    0.44
     Spannung
    0.44
    Spotify
    0.43
    Change
    0.42
     phenomena
    0.42
    麓
    0.42
    CL
    0.41
     fenô
    0.41
    POSITIVE LOGITS
    ograd
    0.48
     επικ
    0.48
    veh
    0.47
    ési
    0.46
    ographic
    0.45
     assigned
    0.45
    onton
    0.44
    šao
    0.44
     преимуще
    0.44
    らは
    0.44
    Activations Density 0.000%

    No Known Activations