© 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. 155
    Prev
    Next
    INDEX
    Explanations

    s followed by 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_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
    t
    0.66
    is
    0.65
    i
    0.64
    in
    0.61
    l
    0.58
    r
    0.54
    h
    0.54
    u
    0.53
    en
    0.53
    as
    0.53
    POSITIVE LOGITS
     underpinned
    0.64
     untenable
    0.63
     devenu
    0.62
     undeniably
    0.60
    <unused497>
    0.60
     admirable
    0.58
     supposed
    0.58
     blevet
    0.57
     commendable
    0.57
    <unused2107>
    0.57
    Activations Density 1.791%

    No Known Activations