© 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. 33832
    Prev
    Next
    INDEX
    Explanations

    sentence delimiters and subsequent phrases

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

    multi-step planning

    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
     গুজব
    0.43
    getCharAt
    0.42
     showAlert
    0.41
    ဋ
    0.41
     مُ
    0.40
    ︹
    0.40
     يُ
    0.39
     تُ
    0.38
     če
    0.37
    graphHead
    0.37
    POSITIVE LOGITS
    ichtig
    0.41
     হুমায়
    0.41
    energie
    0.40
    any
    0.40
    aching
    0.39
    anque
    0.39
    apport
    0.39
    Describe
    0.38
    
    0.38
    iger
    0.37
    Activations Density 0.084%

    No Known Activations