© 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. 8990
    Prev
    Next
    INDEX
    Explanations

    punctuation and common words

    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
    ↘
    1.13
    esque
    1.12
     reminder
    1.12
    ed
    1.08
     sentencing
    1.04
    overs
    1.03
     temptation
    1.02
    nash
    1.02
    적인
    1.01
     grinning
    1.01
    POSITIVE LOGITS
    ことなく
    1.20
    𝗛
    1.15
    वर्ण
    1.12
    𝙎
    1.10
    𝗟
    1.10
    𝙃
    1.10
    ूरती
    1.08
    ri
    1.08
    𝙍
    1.08
    ร
    1.07
    Activations Density 0.003%

    No Known Activations