© 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. 96856
    Prev
    Next
    INDEX
    Explanations

    with me

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

    system states and nodes

    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
    ق
    0.57
    ett
    0.53
    ون
    0.50
    لي
    0.50
    q
    0.50
    ek
    0.49
    ল
    0.49
    ের
    0.48
    প
    0.48
    ReturnType
    0.47
    POSITIVE LOGITS
     waveforms
    0.49
     optimizations
    0.45
     conveyed
    0.45
     converters
    0.44
     discretized
    0.44
     PCM
    0.44
     obeys
    0.43
     emitted
    0.42
     conforming
    0.42
     shipped
    0.42
    Activations Density 0.000%

    No Known Activations