© 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. 148071
    Prev
    Next
    INDEX
    Explanations

    successful growth

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

    escalation or potential consequences

    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
    ils
    0.50
    ili
    0.49
    𝗥
    0.48
    insa
    0.47
     rusa
    0.45
    ika
    0.45
    ılar
    0.44
    ince
    0.43
    ene
    0.43
    amas
    0.43
    POSITIVE LOGITS
     streets
    0.47
    الية
    0.46
    悄
    0.46
    тре
    0.46
    通
    0.46
    保留
    0.45
     parked
    0.45
     balcon
    0.44
     wedges
    0.44
     oppervlak
    0.44
    Activations Density 0.001%

    No Known Activations