© 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. 128044
    Prev
    Next
    INDEX
    Explanations

    use to describe a capability

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

    million different unsettling

    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
     মৃ
    0.55
    пар
    0.53
    박
    0.49
    첫
    0.49
    上
    0.48
    номи
    0.47
    за
    0.46
    折
    0.46
    鲷
    0.46
    ваете
    0.46
    POSITIVE LOGITS
     dispose
    0.44
     dilengkapi
    0.44
     repaint
    0.43
     paralel
    0.42
     rarement
    0.42
     anglès
    0.42
     sanit
    0.41
     countrymen
    0.41
     VEL
    0.41
    選手の
    0.41
    Activations Density 0.001%

    No Known Activations