© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 576
    Prev
    Next
    INDEX
    Explanations

    self-description of capabilities and training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    and
    0.67
    C
    0.66
    c
    0.64
    P
    0.63
    t
    0.62
    A
    0.59
    L
    0.58
    S
    0.58
    G
    0.58
    T
    0.58
    POSITIVE LOGITS
     usefulness
    0.66
     perseverance
    0.65
     unwavering
    0.63
     directive
    0.61
     masterful
    0.60
     ability
    0.60
     relentless
    0.60
     pemberian
    0.59
     overarching
    0.59
     insistence
    0.59
    Activations Density 0.375%

    No Known Activations