© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44385
    Prev
    Next
    INDEX
    Explanations

    words followed by specific terms

    np_acts-logits-general · gemini-2.5-flash-lite

    account of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Performing
    0.48
    o
    0.48
     Egg
    0.46
     sẽ
    0.46
     Negeri
    0.46
     So
    0.45
    会
    0.44
    0.44
    <0xE3>
    0.43
    返回
    0.43
    POSITIVE LOGITS
     divs
    0.56
    ⟋
    0.55
     だっ
    0.53
    <unused40>
    0.52
     スター
    0.50
     shielded
    0.50
    lovepoetry
    0.50
    𝘞
    0.50
    iterations
    0.49
    たちが
    0.49
    Activations Density 0.000%

    No Known Activations