© 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. 60860
    Prev
    Next
    INDEX
    Explanations

    industry specific

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

    suicidal ideation, problems

    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
    ユー
    0.49
    디어
    0.48
    .
    0.47
    jur
    0.46
    dia
    0.45
    vk
    0.44
     waarin
    0.44
    Skippable
    0.44
    datepicker
    0.44
     vbox
    0.43
    POSITIVE LOGITS
     ضر
    0.50
     renal
    0.50
    硌
    0.49
     potholes
    0.48
    延续
    0.47
     पाने
    0.46
    咐
    0.46
    驮
    0.46
    ចែក
    0.46
    inį
    0.46
    Activations Density 0.000%

    No Known Activations