© 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. 31724
    Prev
    Next
    INDEX
    Explanations

    branching, solving, nesting, barking

    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
     accessibles
    0.42
     elites
    0.42
     pione
    0.41
    Tyler
    0.41
     sacrificed
    0.41
    精英
    0.41
    Con
    0.40
    ب
    0.40
    去世
    0.40
    Di
    0.40
    POSITIVE LOGITS
    ారని
    0.44
     Sellers
    0.43
    くなります
    0.43
     уров
    0.42
    akaran
    0.40
    tration
    0.40
     Xmas
    0.40
    micronaut
    0.40
     মার
    0.39
     понятно
    0.39
    Activations Density 0.000%

    No Known Activations