© 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. 208580
    Prev
    Next
    INDEX
    Explanations

    continuing or increasing

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

    primary, crucial, final steps

    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
    Jadi
    0.60
    STATE
    0.59
    FRE
    0.54
    Departamento
    0.52
    KEYS
    0.50
    INFINITY
    0.50
    㞱
    0.50
    公子
    0.50
    론
    0.50
    tım
    0.49
    POSITIVE LOGITS
     droughts
    0.52
     between
    0.47
     hypoxic
    0.46
     fluids
    0.45
    icha
    0.44
     during
    0.44
     shielding
    0.43
     hydrothermal
    0.43
     natural
    0.43
     referee
    0.43
    Activations Density 0.000%

    No Known Activations