© 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. 164565
    Prev
    Next
    INDEX
    Explanations

    sequences after specific words

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

    describing states or conditions

    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
     angi
    0.49
     occur
    0.48
    di
    0.46
     attend
    0.45
    j
    0.44
    S
    0.44
     sort
    0.43
     Sort
    0.42
    複
    0.42
    Ｃ
    0.42
    POSITIVE LOGITS
     майже
    0.61
     Muitos
    0.58
     کبھی
    0.57
     завжди
    0.56
     многим
    0.55
     esfuer
    0.54
     почти
    0.54
     tantos
    0.53
     bijna
    0.53
     penchant
    0.53
    Activations Density 0.130%

    No Known Activations