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. 17-GEMMASCOPE-2-RES-65K
    4. 47594
    Prev
    Next
    INDEX
    Explanations

    accessibility

    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_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
    🎋
    1.50
    🔳
    1.49
    시키
    1.48
    💮
    1.43
    🔘
    1.41
     poesía
    1.41
    💏
    1.41
    🕋
    1.40
     llamadas
    1.38
     bañ
    1.38
    POSITIVE LOGITS
    us
    1.34
     absolutely
    1.18
    cle
    1.16
    𝓪
    1.12
    at
    1.10
    information
    1.09
     thinly
    1.07
    cu
    1.06
     obstructive
    1.05
     terminating
    1.02
    Activations Density 0.000%

    No Known Activations