© 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. 156144
    Prev
    Next
    INDEX
    Explanations

    interviewing the, two specialty

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

    instead focus

    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
    intervals
    0.52
    ۲۰
    0.51
    Clinic
    0.50
    Credential
    0.50
    Catalogue
    0.50
    aturamento
    0.49
    浱
    0.49
    葲
    0.49
    transitions
    0.49
    körper
    0.49
    POSITIVE LOGITS
     Platts
    0.54
     ignition
    0.54
     proxy
    0.53
     cups
    0.52
     acne
    0.52
     rematch
    0.52
     zombie
    0.52
     anon
    0.50
     dimerization
    0.50
     latent
    0.50
    Activations Density 0.000%

    No Known Activations