© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18119
    Prev
    Next
    INDEX
    Explanations

    by state

    np_acts-logits-general · gemini-2.5-flash-lite

    produce more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cùng
    0.48
     સાથે
    0.48
     செய்யவும்
    0.45
     함께
    0.44
    ཌ
    0.43
    摡
    0.42
    patial
    0.42
    isection
    0.42
     확장
    0.42
     합동
    0.41
    POSITIVE LOGITS
    ↵
    0.43
     vodi
    0.43
     nerfs
    0.42
     trash
    0.42
    คุณ
    0.40
     davvero
    0.40
     runner
    0.39
     nerf
    0.39
     técn
    0.39
     prü
    0.38
    Activations Density 0.000%

    No Known Activations