© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9222
    Prev
    Next
    INDEX
    Explanations

    brick and block specification standards

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

    generalization

    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_40_width_16k_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
    榭
    0.44
    ፃ
    0.43
     remettre
    0.41
     Drainage
    0.40
     услуг
    0.40
     ремонта
    0.40
     पुरंदरे
    0.40
     Hose
    0.39
    ꗥ
    0.39
    车型
    0.39
    POSITIVE LOGITS
    tml
    0.52
    vskip
    0.48
    stat
    0.47
    bandits
    0.43
     bandits
    0.43
     bandit
    0.43
     bricks
    0.42
     PML
    0.42
     graphon
    0.41
     Theoret
    0.41
    Activations Density 0.018%

    No Known Activations