© 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. 22-GEMMASCOPE-RES-131K
    7. 72747
    Prev
    Next
    INDEX
    Explanations

    consequence or later outcome

    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_22/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
     both
    -1.89
     både
    -1.51
     these
    -1.45
    などの
    -1.41
    <bos>
    -1.37
    がありますが
    -1.34
    both
    -1.31
     sowohl
    -1.25
     Mú
    -1.23
     either
    -1.23
    POSITIVE LOGITS
     später
    1.30
     eventually
    1.28
     Ultimately
    1.27
     ultimately
    1.19
     Eventually
    1.18
    Ultimately
    1.18
     subsequently
    1.14
    為に
    1.13
    ようです
    1.13
     later
    1.13
    Activations Density 0.060%

    No Known Activations