© 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. 239999
    Prev
    Next
    INDEX
    Explanations

    future predictions and outcomes

    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
     વખતે
    0.50
     સમયે
    0.47
    늠
    0.46
     precisar
    0.45
     সময়ে
    0.45
     videojuegos
    0.45
    новая
    0.44
    ச
    0.44
    κτήθηκε
    0.44
     Spieler
    0.43
    POSITIVE LOGITS
    nominated
    0.57
     elev
    0.51
    expected
    0.50
     mnoh
    0.49
     beh
    0.47
     mins
    0.44
     اتح
    0.44
     సన్ని
    0.44
    forestry
    0.44
     gef
    0.43
    Activations Density 0.001%

    No Known Activations