© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7134
    Prev
    Next
    INDEX
    Explanations

    words starting with hypo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     It
    -2.33
    棪
    -2.08
     were
    -2.08
     района
    -1.96
    .”
    -1.93
     foremost
    -1.82
    までは
    -1.82
    มาะ
    -1.81
     ’
    -1.80
     แต่
    -1.80
    POSITIVE LOGITS
    Toponymie
    2.09
    檍
    2.02
     techniczne
    2.00
     almas
    1.98
    犽
    1.92
    н
    1.90
    3
    1.87
     dotyczące
    1.84
    isation
    1.84
     avantaj
    1.83
    Activations Density 0.035%

    No Known Activations