© 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. 120609
    Prev
    Next
    INDEX
    Explanations

    science viewpoint or approach

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

    no coding required

    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
    NK
    0.56
    natur
    0.50
    Grun
    0.50
     вдруг
    0.50
     мел
    0.50
    <0xC6>
    0.49
    hun
    0.49
    r
    0.49
    m
    0.49
    Vide
    0.48
    POSITIVE LOGITS
     quenching
    0.56
     showering
    0.45
     benchmark
    0.45
     glycemic
    0.44
     glycoprotein
    0.43
     metabolism
    0.43
     taur
    0.42
     showbiz
    0.42
     promotion
    0.42
     phoenix
    0.42
    Activations Density 0.000%

    No Known Activations