© 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. 45797
    Prev
    Next
    INDEX
    Explanations

    registration concept purpose against DAB

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

    research intelligence databases

    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
    ानी
    0.54
    ூர்
    0.54
    фо
    0.51
    ົບ
    0.51
    ሄ
    0.50
    मार्ग
    0.50
     megap
    0.49
    Dropout
    0.49
    también
    0.49
     keluar
    0.49
    POSITIVE LOGITS
     (
    0.55
     Body
    0.50
     Estado
    0.48
     wished
    0.47
     Alpha
    0.47
     Anti
    0.46
     into
    0.45
    CTIONS
    0.45
    essions
    0.44
     instructors
    0.44
    Activations Density 0.000%

    No Known Activations