© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8090
    Prev
    Next
    INDEX
    Explanations

    periods of time and duration

    np_acts-logits-general · gemini-2.5-flash-lite

    periods of time and confinement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     momentary
    0.45
    any
    0.43
    s
    0.43
    glicherweise
    0.42
    done
    0.42
    next
    0.40
    ]");
    0.40
    の中に
    0.40
    to
    0.40
    }");
    0.40
    POSITIVE LOGITS
     कार्यकाल
    0.70
     tenure
    0.65
     incarceration
    0.57
     captivity
    0.57
     життя
    0.55
     existencia
    0.52
     incumb
    0.51
     existence
    0.51
    キャリア
    0.50
     existência
    0.50
    Activations Density 0.137%

    No Known Activations