© 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. 34089
    Prev
    Next
    INDEX
    Explanations

    access, count, showroom

    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
     дори
    -0.92
     Parole
    -0.88
     lèvres
    -0.88
     マンガ
    -0.85
    വി
    -0.85
    都需要
    -0.84
     except
    -0.83
     behov
    -0.82
     Hone
    -0.81
     符号
    -0.81
    POSITIVE LOGITS
    }$_
    1.07
    iously
    1.05
     last
    1.03
    }\}$
    1.02
    病例
    1.02
    |$.
    1.01
    iteracy
    1.01
    ]]=
    1.00
    יך
    0.98
     завер
    0.98
    Activations Density 0.005%

    No Known Activations