© 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. 6448
    Prev
    Next
    INDEX
    Explanations

    learning, distinguishing, ideas, sense

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

    figuring out

    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
     теркәлүсез
    0.48
     परंतु
    0.44
     ২০২২
    0.43
    ❣️
    0.43
    akkhati
    0.42
    ₺
    0.41
    令和
    0.41
     ২০২৩
    0.41
    ylmethylsulfanyl
    0.41
    𝘁
    0.40
    POSITIVE LOGITS
     thằng
    0.55
     crappy
    0.50
     cosas
    0.48
     lvl
    0.47
     booze
    0.46
     boobs
    0.46
     shitty
    0.46
     recieved
    0.46
     badass
    0.45
     cuz
    0.44
    Activations Density 0.049%

    No Known Activations