© 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. 3948
    Prev
    Next
    INDEX
    Explanations

    lean management

    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
    矜
    1.28
     Rostov
    1.27
    本科
    1.26
     Floren
    1.21
    kannten
    1.21
    Parameter
    1.20
    别人的
    1.19
    凛
    1.18
    Bachelor
    1.18
    rank
    1.18
    POSITIVE LOGITS
     solution
    1.47
     solve
    1.41
     solutions
    1.39
     (’
    1.38
     winner
    1.36
    槓
    1.33
    fmt
    1.32
    !;
    1.31
    ទ្រ
    1.30
     resolving
    1.30
    Activations Density 0.005%

    No Known Activations