© 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. 245038
    Prev
    Next
    INDEX
    Explanations

    successful results

    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
     flats
    0.52
     apartamentos
    0.52
     Sverige
    0.50
     opos
    0.50
     frase
    0.49
     afiliados
    0.49
     branco
    0.49
    -
    0.48
     residencial
    0.48
     semicol
    0.47
    POSITIVE LOGITS
    ješt
    0.50
    作った
    0.47
     રે
    0.46
     માહિતી
    0.44
    েন
    0.44
     лежа
    0.42
    ClFN
    0.42
    c
    0.42
    ค
    0.42
     ગો
    0.41
    Activations Density 0.000%

    No Known Activations