© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4866
    Prev
    Next
    INDEX
    Explanations

    depending on or suited for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    во
    1.33
    ->
    1.31
    ként
    1.23
     instead
    1.20
    切实
    1.19
    ཙ
    1.18
     tuss
    1.18
    的身
    1.17
    することで
    1.16
    нее
    1.15
    POSITIVE LOGITS
     dependen
    1.28
    depending
    1.20
    reliance
    1.10
    뎁
    1.10
     Bracken
    1.10
    ridden
    1.08
     tergantung
    1.04
    ถ้า
    1.02
     bergantung
    1.02
     dépend
    1.01
    Activations Density 0.174%

    No Known Activations