© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65343
    Prev
    Next
    INDEX
    Explanations

    su followed by words like cu, aa, dom, itor, ella, rimi, id

    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
    .
    -3.03
    ])))
    -2.84
    If
    -2.77
    d
    -2.73
    ]));
    -2.73
    頃に
    -2.73
    m
    -2.69
    no
    -2.64
    頃の
    -2.61
    嫗
    -2.56
    POSITIVE LOGITS
    言えば
    3.05
    いえば
    2.80
     was
    2.70
    言うと
    2.56
    เกง
    2.55
    臾
    2.48
    踱
    2.34
    Ɑ
    2.30
    剜
    2.30
    軾
    2.30
    Activations Density 0.026%

    No Known Activations