© 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
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1407
    Prev
    Next
    INDEX
    Explanations

    ggy, 33 sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
     herb
    0.67
    ➙
    0.65
     trypt
    0.64
     ESG
    0.61
    iral
    0.60
     suboptimal
    0.59
     Chab
    0.59
    ᱹ
    0.59
    🛹
    0.58
     elevation
    0.58
    POSITIVE LOGITS
    kk
    1.46
    PPPP
    1.35
    KK
    1.35
    cccc
    1.31
    zz
    1.20
    rrrr
    1.18
    MM
    1.15
    nn
    1.14
    HHHH
    1.14
    UU
    1.13
    Activations Density 0.713%

    No Known Activations