© 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. 136991
    Prev
    Next
    INDEX
    Explanations

    SIMAP. For all

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

    acknowledge responsibility

    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
     efeito
    0.55
     Porém
    0.51
     pesquis
    0.48
     devenue
    0.47
     płyt
    0.47
    鈈
    0.47
     amplo
    0.47
     logró
    0.47
     reação
    0.47
     função
    0.47
    POSITIVE LOGITS
    ል
    0.48
     overlaid
    0.48
    ";
    0.45
     नै
    0.44
     مرتب
    0.42
    itele
    0.42
     overl
    0.42
    mans
    0.41
    eting
    0.41
    mi
    0.41
    Activations Density 0.001%

    No Known Activations