© 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. 189350
    Prev
    Next
    INDEX
    Explanations

    groups of or teachers

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

    determining if something is a blockage

    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
     continuo
    0.50
     přip
    0.50
    Ρ
    0.43
     Namely
    0.43
     şi
    0.43
     pripre
    0.42
    隆
    0.41
     walaupun
    0.41
    저는
    0.41
    ↵↵
    0.40
    POSITIVE LOGITS
    ிறது
    0.48
     जंग
    0.47
     unwarrant
    0.47
     شہریوں
    0.46
    ి
    0.46
     അഭിപ്
    0.46
    äh
    0.46
     వారి
    0.46
    sembles
    0.45
     متعدد
    0.45
    Activations Density 0.000%

    No Known Activations