© 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. 31109
    Prev
    Next
    INDEX
    Explanations

    estamos fallando

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

    keywords followed by punctuation or specific words

    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
     Memorial
    0.48
     Eds
    0.47
     Ed
    0.46
    )()
    0.46
     R
    0.46
     Investig
    0.46
                             
    0.45
     Asphalt
    0.45
                                   
    0.45
     James
    0.44
    POSITIVE LOGITS
    ﮏ
    0.52
     potrà
    0.52
    名人
    0.51
    Ⲉ
    0.51
    木
    0.51
    ᵐ
    0.50
    🔙
    0.50
    ￫
    0.50
    ندان
    0.50
    โม
    0.48
    Activations Density 0.000%

    No Known Activations