© 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. 157078
    Prev
    Next
    INDEX
    Explanations

    package damage or rejection

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

    concept, church, contact, vulnerabilities

    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
    T
    0.58
    Н
    0.53
    Ми
    0.52
    L
    0.52
    ام
    0.52
    Spanish
    0.52
    N
    0.52
    МИ
    0.51
    Gabriel
    0.50
    ين
    0.50
    POSITIVE LOGITS
     interfaces
    0.50
     molds
    0.46
    する場合は
    0.46
    ibrated
    0.46
     fluids
    0.44
     veins
    0.43
     Fluids
    0.43
     transports
    0.42
     tunnels
    0.42
     digests
    0.42
    Activations Density 0.000%

    No Known Activations