© 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. 116333
    Prev
    Next
    INDEX
    Explanations

    things and spaces

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

    computer technology and specifications

    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
    -------------
    0.53
     teknik
    0.52
    ৩৯
    0.51
    കേന്ദ്രം
    0.51
     Abschluss
    0.50
     técnico
    0.49
     amerikan
    0.48
    খার
    0.47
    jedno
    0.47
    SB
    0.46
    POSITIVE LOGITS
     prec
    0.48
     balconies
    0.47
     carpets
    0.45
    사와
    0.44
    })$,
    0.43
     pref
    0.43
     wallpapers
    0.42
     blossoms
    0.41
     podia
    0.41
     duality
    0.40
    Activations Density 0.000%

    No Known Activations