© 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. 124374
    Prev
    Next
    INDEX
    Explanations

    work after a treatment

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

    technical systems and design

    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
     mangrove
    0.51
    มอบ
    0.47
     Singapore
    0.42
     Muslims
    0.42
     mangroves
    0.42
    会
    0.41
     Surgical
    0.41
     transformative
    0.40
    得很
    0.40
     effecting
    0.40
    POSITIVE LOGITS
    notas
    0.50
    Cha
    0.50
    anych
    0.49
    Delay
    0.48
    alakip
    0.47
    Quanto
    0.47
    Ψ
    0.45
    ajah
    0.44
    dicke
    0.44
    sah
    0.44
    Activations Density 0.000%

    No Known Activations