© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 121246
    Prev
    Next
    INDEX
    Explanations

    foreign language punctuation

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

    type, organization, children

    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
    ዎት
    0.52
     krishna
    0.49
     máquina
    0.48
    전에
    0.48
    ällä
    0.47
     quỹ
    0.47
    깨
    0.46
     Multis
    0.45
     cadeia
    0.45
     zéro
    0.44
    POSITIVE LOGITS
    ]
    0.56
    ٬
    0.55
    }
    0.54
    }$\\
    0.47
     اعلام
    0.46
     সংবাদ
    0.46
     пресс
    0.46
    らは
    0.45
     خبرنگ
    0.45
    invited
    0.45
    Activations Density 0.000%

    No Known Activations