© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 29645
    Prev
    Next
    INDEX
    Explanations

    stealing cookies and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SO
    0.46
    мі
    0.43
    P
    0.43
    SOUR
    0.42
    oz
    0.42
    çok
    0.41
    SPACE
    0.40
    optional
    0.40
    Repair
    0.40
    M
    0.40
    POSITIVE LOGITS
     cramps
    0.45
     Adventures
    0.43
     bassist
    0.42
     Ingl
    0.42
     distillery
    0.42
     начну
    0.42
     adventures
    0.41
     చేరు
    0.41
     trembling
    0.41
     Ansible
    0.41
    Activations Density 0.012%

    No Known Activations