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. 1591
    Prev
    Next
    INDEX
    Explanations

    LLM / LLMs

    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
     XXX
    0.67
    тория
    0.59
     CCCC
    0.59
    órios
    0.56
    atorios
    0.56
     ல
    0.55
     AAA
    0.55
     DDD
    0.54
     JJ
    0.54
     cia
    0.54
    POSITIVE LOGITS
    Rs
    0.70
    Ms
    0.68
    Cs
    0.67
    Bs
    0.67
    Ps
    0.66
    Ds
    0.66
    Fs
    0.64
    Gs
    0.63
    M
    0.61
    Ts
    0.59
    Activations Density 0.572%

    No Known Activations