© 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. 157958
    Prev
    Next
    INDEX
    Explanations

    states, tradition, plan, funding, flour

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

    compound words and technical terms

    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
    팎
    0.46
     PDEs
    0.45
    etapkan
    0.45
    }+{
    0.43
     जीवा
    0.43
    }_{
    0.42
    ₂+
    0.42
    utscher
    0.42
     visione
    0.41
    ètres
    0.40
    POSITIVE LOGITS
    স
    0.67
     Prostate
    0.45
    hug
    0.45
    सीजी
    0.43
     നിന്നും
    0.43
     mutter
    0.42
    Ꭲ
    0.41
    tube
    0.41
    ໌
    0.41
    ㄎ
    0.41
    Activations Density 0.001%

    No Known Activations