© 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. 234837
    Prev
    Next
    INDEX
    Explanations

    Android Development

    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
     weeds
    0.55
     सेक्स
    0.54
     쓰
    0.52
     ఇప్పటి
    0.52
     trí
    0.48
     shackles
    0.46
     ideologies
    0.45
     eels
    0.45
     villains
    0.44
     쓸
    0.43
    POSITIVE LOGITS
    e
    0.64
    f
    0.53
    a
    0.52
    ه
    0.52
     BEN
    0.51
     تقد
    0.51
    FAE
    0.49
     keterangan
    0.49
     altera
    0.48
     SIE
    0.48
    Activations Density 0.000%

    No Known Activations