© 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. 4202
    Prev
    Next
    INDEX
    Explanations

    legal advice after average

    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
    nya
    4.63
    t
    4.01
    n
    3.96
    こと
    3.85
    sy
    3.84
    ly
    3.81
    nent
    3.75
    s
    3.56
    sch
    3.55
    ded
    3.48
    POSITIVE LOGITS
    verage
    2.04
    7
    2.03
    8
    1.80
    ffected
    1.76
    asList
    1.57
    ísmo
    1.53
    3
    1.53
    ekwondo
    1.52
    くちゃ
    1.52
    9
    1.50
    Activations Density 0.193%

    No Known Activations