© 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. 112268
    Prev
    Next
    INDEX
    Explanations

    Bridge International Orange

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

    abstract concepts and 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
    ેર
    0.44
     इंटरनेट
    0.42
    detected
    0.40
     cục
    0.40
    리티
    0.39
    ansky
    0.39
    ้
    0.39
    ns
    0.38
     Internet
    0.38
    敌人
    0.38
    POSITIVE LOGITS
     möglicherweise
    0.53
     ungew
    0.49
     volle
    0.45
    Willow
    0.45
     blieb
    0.44
     ausreiche
    0.44
     শীঘ্রই
    0.42
    一座
    0.42
    АСС
    0.42
     ইউনিক
    0.42
    Activations Density 0.001%

    No Known Activations