© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 64336
    Prev
    Next
    INDEX
    Explanations

    then there's

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

    generating stories

    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
    0.49
    нице
    0.45
     MARRI
    0.45
    idae
    0.44
    9
    0.44
     Messrs
    0.43
    3
    0.42
     устанавли
    0.41
    6
    0.41
    LEY
    0.41
    POSITIVE LOGITS
     violación
    0.47
     kanya
    0.45
     ficou
    0.43
     calmness
    0.43
    是一個
    0.41
     mysticism
    0.41
     jurul
    0.41
     fidèle
    0.41
    ग्राउंड
    0.41
     maneiras
    0.40
    Activations Density 0.000%

    No Known Activations