© 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. 34-GEMMASCOPE-RES-131K
    7. 47770
    Prev
    Next
    INDEX
    Explanations

    timestamps with timezones

    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_34/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
     Jahrgang
    -0.86
    yr
    -0.76
     beautiful
    -0.76
    낡
    -0.76
    thday
    -0.75
     daylight
    -0.75
    ліза
    -0.74
    𝑅
    -0.74
     thru
    -0.73
    qld
    -0.73
    POSITIVE LOGITS
    }+
    0.85
     Ryanair
    0.82
    utenant
    0.74
     psicológica
    0.73
     Giovanna
    0.73
     Zionist
    0.73
    Mariana
    0.73
    檗
    0.73
    Impression
    0.73
    モロ
    0.73
    Activations Density 0.025%

    No Known Activations