© 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. 110732
    Prev
    Next
    INDEX
    Explanations

    reading formining apparatuscompany profilesasset value

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

    people telling me things

    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
    किम
    0.50
    ले
    0.50
    腓
    0.48
     regione
    0.47
    द्दीन
    0.46
     терро
    0.46
    रीय
    0.46
    ುಂಬ
    0.46
    ემი
    0.46
     diosa
    0.46
    POSITIVE LOGITS
     presenters
    0.49
     coincide
    0.46
    gt
    0.44
     +
    0.44
    ever
    0.43
    ritual
    0.43
     readings
    0.42
    短短
    0.42
     coincides
    0.42
    halt
    0.41
    Activations Density 0.000%

    No Known Activations