© 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. 49321
    Prev
    Next
    INDEX
    Explanations

    groups on request

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

    inevitably lead

    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
    iggle
    0.48
    ೀರ
    0.44
    ∕
    0.44
    ezers
    0.43
    ặp
    0.42
     Professors
    0.42
    储
    0.42
    躯
    0.42
    öglichkeiten
    0.41
    ڑوں
    0.40
    POSITIVE LOGITS
    number
    0.50
    不超过
    0.46
     пре
    0.45
     Luo
    0.45
    nam
    0.45
     כש
    0.45
     正規
    0.45
     კან
    0.44
    隗
    0.44
     informe
    0.43
    Activations Density 0.000%

    No Known Activations