© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4644
    Prev
    Next
    INDEX
    Explanations

    code with functions and definitions

    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
     صحت
    0.81
    oughed
    0.70
    愎
    0.65
    etches
    0.64
     Brought
    0.56
     جماعه
    0.55
     confounded
    0.54
    入
    0.54
    ushes
    0.53
    гана
    0.52
    POSITIVE LOGITS
     Alam
    2.85
     théra
    2.81
     bip
    2.81
     dharm
    2.80
     flores
    2.74
     oliv
    2.74
    🌲
    2.73
     Akademi
    2.73
    🏔
    2.71
     splend
    2.71
    Activations Density 0.005%

    No Known Activations