© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9372
    Prev
    Next
    INDEX
    Explanations

    communication and specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    0.60
    $
    0.52
    =
    0.50
    ftar
    0.50
    Bon
    0.45
    Gain
    0.44
    –
    0.44
    --
    0.44
    $-
    0.44
    Purpose
    0.44
    POSITIVE LOGITS
    opatra
    0.48
     যোগাযোগ
    0.45
    ौती
    0.43
    ন্না
    0.43
    र्यंत
    0.42
     života
    0.42
     ശങ്ക
    0.40
    ്ല
    0.40
     communicate
    0.40
     коммуника
    0.40
    Activations Density 0.018%

    No Known Activations