© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8367
    Prev
    Next
    INDEX
    Explanations

    filling with concern

    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
    Аль
    1.25
    EN
    1.22
    OY
    1.22
    НЫ
    1.21
     والاست
    1.18
    н
    1.16
    ी
    1.16
    ਠ
    1.15
    ឍ
    1.14
    ність
    1.13
    POSITIVE LOGITS
    ο
    1.23
     lui
    1.11
    ppin
    1.03
     reúne
    1.02
    𝘷
    1.02
    𝘴
    1.01
     giusto
    1.01
    o
    1.00
    0.99
     extrapolate
    0.98
    Activations Density 0.000%

    No Known Activations