© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38558
    Prev
    Next
    INDEX
    Explanations

    places or people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }}\
    0.45
    }}$$
    0.43
     intimidate
    0.42
    ת
    0.42
     mis
    0.41
    кен
    0.41
    كبر
    0.41
    కార
    0.40
     Ра
    0.40
    Ре
    0.39
    POSITIVE LOGITS
     puisque
    0.51
    綸
    0.45
     Photographic
    0.44
     eftersom
    0.43
    conductivity
    0.43
     koos
    0.42
     poiché
    0.42
    ຈາກ
    0.42
    𝚄
    0.42
     wären
    0.42
    Activations Density 0.000%

    No Known Activations