© 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. 130524
    Prev
    Next
    INDEX
    Explanations

    65 years of age or older

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

    manufacturer offer, no more, needs ahead

    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
    圿
    0.49
    <unused426>
    0.49
     Amts
    0.47
    伌
    0.47
     čís
    0.46
     опасность
    0.46
     annihilated
    0.45
     Legisl
    0.45
    নন্দ
    0.44
    <unused234>
    0.44
    POSITIVE LOGITS
    e
    0.58
    essayer
    0.57
    ou
    0.52
    ik
    0.51
    ect
    0.50
    ets
    0.50
    ax
    0.50
     grapefruit
    0.50
    oc
    0.50
    utes
    0.50
    Activations Density 0.000%

    No Known Activations