© 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-16K
    7. 12464
    Prev
    Next
    INDEX
    Explanations

    partner or shop

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

    partner, buddy, builder, rolled into one

    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_16k_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
     ו
    0.47
    ವೆ
    0.46
     handen
    0.45
    <0xDA>
    0.45
    及
    0.44
     lương
    0.42
     או
    0.42
    高端
    0.40
    薦
    0.40
    高手
    0.40
    POSITIVE LOGITS
    fabricated
    0.52
     Studying
    0.48
    computed
    0.47
     ternary
    0.47
    RENCE
    0.46
     Statistical
    0.44
     STAT
    0.44
     SCIENCES
    0.44
     computed
    0.43
     metastable
    0.42
    Activations Density 0.000%

    No Known Activations