© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8409
    Prev
    Next
    INDEX
    Explanations

    address, US dollar, puppy play, around

    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_9_width_262k_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
    1.39
     majority
    1.29
    𝙎
    1.26
    По
    1.25
    majority
    1.25
    𝙈
    1.23
    UserPool
    1.23
    𝙋
    1.22
    Ис
    1.21
    𝙃
    1.21
    POSITIVE LOGITS
    د
    1.32
    風味
    1.28
    indent
    1.24
     fain
    1.15
    валися
    1.10
    ването
    1.10
     élections
    1.08
    主办
    1.07
    ために
    1.06
    νή
    1.06
    Activations Density 0.000%

    No Known Activations