© 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. 199815
    Prev
    Next
    INDEX
    Explanations

    earnings beat

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

    physical phenomena and movement

    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
     президента
    0.54
    𝘯
    0.53
     குழந்தைகள்
    0.52
     максимально
    0.52
     मैनेजर
    0.52
     வெற்ற
    0.52
     грамо
    0.49
     enfermos
    0.49
     семьи
    0.49
    𒈬
    0.48
    POSITIVE LOGITS
     Turquoise
    0.45
    ;
    0.44
     scen
    0.43
     sk
    0.42
     barb
    0.41
     styl
    0.41
     trough
    0.41
     toward
    0.40
     showbiz
    0.40
     cool
    0.40
    Activations Density 0.001%

    No Known Activations