© 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. 40026
    Prev
    Next
    INDEX
    Explanations

    young or new beginnings

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

    harmful activities due to distress

    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
     எப்போதும்
    0.46
    axon
    0.44
    ષ
    0.42
     Петра
    0.41
     ব্যার্থ
    0.41
     アウトドア
    0.41
    >',
    0.40
    otherapeutic
    0.40
    𝓾
    0.39
     аўта
    0.39
    POSITIVE LOGITS
     reasons
    0.44
     younger
    0.44
     tempor
    0.43
     derzeit
    0.43
     Danach
    0.43
     jovens
    0.42
     young
    0.41
     perman
    0.41
     Perman
    0.41
     giovani
    0.40
    Activations Density 0.030%

    No Known Activations