© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3727
    Prev
    Next
    INDEX
    Explanations

    words starting with "what", "i", "you"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_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
    とともに
    1.69
    ો
    1.42
    \">
    1.41
    "});
    1.34
    ron
    1.33
    </h6>
    1.31
     goblet
    1.31
    َ
    1.30
    ha
    1.30
    ों
    1.28
    POSITIVE LOGITS
    w
    1.84
    H
    1.82
    R
    1.64
    S
    1.60
    ó
    1.54
    b
    1.51
    ა
    1.49
    F
    1.47
    P
    1.45
    c
    1.44
    Activations Density 0.709%

    No Known Activations