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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 41272
    Prev
    Next
    INDEX
    Explanations

    attack vector

    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
    .**
    0.41
     and
    0.40
    .°
    0.38
    .
    0.37
    ––
    0.36
    ¹.
    0.34
     (**
    0.34
    —
    0.33
     alongside
    0.33
    ,
    0.32
    POSITIVE LOGITS
     тях
    0.27
     perceptual
    0.27
    രുവനന്തപുരം
    0.27
     দিকের
    0.26
     отношению
    0.26
    হইল
    0.25
    渶
    0.25
    tokenizer
    0.25
    Nhap
    0.24
    staticmethod
    0.24
    Activations Density 0.000%

    No Known Activations