Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 365
    Prev
    Next
    INDEX
    Explanations

    words starting with c

    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_29_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
    crim
    0.72
     Hurt
    0.72
    l
    0.70
    literally
    0.67
     helpful
    0.67
    ls
    0.66
    houses
    0.66
     embellished
    0.66
    cic
    0.64
    libc
    0.64
    POSITIVE LOGITS
    ording
    1.20
    umbent
    1.18
    rossover
    1.12
    unningham
    1.10
    rimin
    1.09
    uckoo
    1.09
    ̧
    1.07
    ounsel
    1.06
    uidado
    1.04
    rypted
    1.04
    Activations Density 0.266%

    No Known Activations