© 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. 127019
    Prev
    Next
    INDEX
    Explanations

    fast movement and performance

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

    connects components, avoids issues, limited functionality, DNA strand, prevents damage

    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
    فن
    0.46
     应用
    0.43
     Quillen
    0.42
     اصول
    0.42
     তারাও
    0.41
     also
    0.40
     principes
    0.40
    安
    0.40
     interpre
    0.39
    Tinh
    0.39
    POSITIVE LOGITS
    łac
    0.48
    ્ર
    0.47
    Inspection
    0.47
    ritu
    0.47
    ramiento
    0.46
    мни
    0.46
    company
    0.46
     सूरत
    0.45
     பெரும்பாலான
    0.44
    nál
    0.44
    Activations Density 0.001%

    No Known Activations