© 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-16K
    7. 1131
    Prev
    Next
    INDEX
    Explanations

    words starting with h

    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_16k_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
     astfel
    2.15
    岖
    2.15
    ędzy
    2.13
    驰
    1.93
    每一次
    1.88
    arzy
    1.87
    屑
    1.86
    казать
    1.84
     sociis
    1.81
    过
    1.78
    POSITIVE LOGITS
    hhh
    1.69
    rac
    1.47
    ゚
    1.41
    hhhh
    1.38
    obbies
    1.33
    omicide
    1.33
    okkaido
    1.32
    irstyle
    1.32
    dip
    1.31
    mmm
    1.30
    Activations Density 0.099%

    No Known Activations