© 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. 112697
    Prev
    Next
    INDEX
    Explanations

    ways that

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

    seeds, milk, population

    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
     który
    0.49
    rendre
    0.49
    𝓪
    0.49
    𝔬
    0.49
    Этот
    0.48
    یت
    0.48
    vgili
    0.48
     futurs
    0.47
     colocando
    0.47
     pakistan
    0.47
    POSITIVE LOGITS
    量
    0.43
    成品
    0.42
    Less
    0.40
    IAB
    0.40
    Lambert
    0.40
    INE
    0.39
     mình
    0.39
    Ig
    0.38
    精品
    0.38
    ポット
    0.38
    Activations Density 0.000%

    No Known Activations