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-65K
    4. 3996
    Prev
    Next
    INDEX
    Explanations

    words starting with a

    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_65k_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
    y
    0.98
    d
    0.93
    r
    0.89
    in
    0.85
    t
    0.85
    l
    0.85
    ম
    0.82
    g
    0.76
    h
    0.75
    র
    0.74
    POSITIVE LOGITS
     partir
    1.26
    rizona
    1.24
     través
    1.22
    UGUST
    1.18
     continuación
    1.17
     priori
    1.16
     pesar
    1.15
    aaaa
    1.14
    aaa
    1.13
    href
    1.13
    Activations Density 0.186%

    No Known Activations