© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2939
    Prev
    Next
    INDEX
    Explanations

    dimly lit, cluttered, quiet states

    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
    日時
    1.39
     utilizamos
    1.20
     imali
    1.17
    時期
    1.14
    (=
    1.13
     organisers
    1.12
     diberi
    1.11
     calendario
    1.10
     (`
    1.10
     ($\
    1.09
    POSITIVE LOGITS
     sigh
    2.43
     pause
    2.40
     softly
    2.28
     faintly
    2.26
     gesturing
    2.24
     trembling
    2.21
     crouching
    2.19
     sighs
    2.19
     hesit
    2.18
     kneeling
    2.18
    Activations Density 1.548%

    No Known Activations