© 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. 74517
    Prev
    Next
    INDEX
    Explanations

    images, inspiration, and pairings

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

    technical structure keywords

    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
     ‘
    0.44
     आणि
    0.44
     and
    0.43
     A
    0.43
    その
    0.41
     Khy
    0.41
     DECL
    0.40
     GRAM
    0.40
     (\
    0.39
     Subsequent
    0.39
    POSITIVE LOGITS
    হরে
    0.50
     stargazerCount
    0.48
    ní
    0.46
    ým
    0.46
    ứ
    0.46
    VerFile
    0.43
    ᱸ
    0.43
     ప్రేక్షకు
    0.42
     విలువ
    0.42
    ídos
    0.42
    Activations Density 0.000%

    No Known Activations