© 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. 116763
    Prev
    Next
    INDEX
    Explanations

    state courts, build muscles, alarm clock

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

    addresses pain points and appeals

    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
    ᱔
    0.55
     wiper
    0.53
    erler
    0.51
     инстру
    0.51
     sinais
    0.51
     thermocou
    0.50
     zupeł
    0.48
     сосредото
    0.48
     első
    0.47
     Lernen
    0.47
    POSITIVE LOGITS
    on
    0.49
    .
    0.49
    م
    0.45
    happiness
    0.43
    м
    0.42
    ه
    0.42
    ذ
    0.41
    mén
    0.41
    購
    0.41
    SESSION
    0.39
    Activations Density 0.000%

    No Known Activations