© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102726
    Prev
    Next
    INDEX
    Explanations

    present progressive or future tense

    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
     when
    -1.70
    },
    -1.63
    </th>
    -1.62
    '));
    
    -1.55
     then
    -1.53
    accepte
    -1.50
    </b>
    -1.49
    掉的
    -1.48
    hamilan
    -1.48
     began
    -1.47
    POSITIVE LOGITS
    as
    1.82
    or
    1.82
    u
    1.81
    of
    1.59
    k
    1.58
    l
    1.52
    with
    1.43
    ang
    1.43
    几个
    1.43
    est
    1.42
    Activations Density 0.119%

    No Known Activations