© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13853
    Prev
    Next
    INDEX
    Explanations

    appears, thoughts, policy

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

    code blocks

    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_16k_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
     authToken
    0.50
     geoLocation
    0.49
     दिसंबर
    0.47
     userInfo
    0.43
     filePath
    0.42
     fileName
    0.42
     userName
    0.42
     _,
    0.41
     lastName
    0.40
     signIn
    0.40
    POSITIVE LOGITS
    renerg
    0.36
    வதில்லை
    0.34
    itching
    0.34
     Ophthalmology
    0.34
     für
    0.33
    vertret
    0.32
    juvant
    0.32
    IUM
    0.32
     Fusarium
    0.32
    箍
    0.32
    Activations Density 0.000%

    No Known Activations