© 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. 187915
    Prev
    Next
    INDEX
    Explanations

    bamboo grove and poles

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

    extracting specific data points

    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
    晒
    0.50
    깆
    0.47
    archiviato
    0.46
     principi
    0.46
    なのですが
    0.45
     ferric
    0.44
     insolvent
    0.44
     sostitu
    0.44
     granular
    0.43
     granularity
    0.42
    POSITIVE LOGITS
     norsk
    0.48
     awards
    0.48
     promises
    0.48
     Niko
    0.45
     県
    0.44
     cartes
    0.44
     Irland
    0.44
    tang
    0.43
    zoek
    0.43
    ชุม
    0.42
    Activations Density 0.000%

    No Known Activations