© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7594
    Prev
    Next
    INDEX
    Explanations

    protecting and preventing

    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_16k_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
    াই
    0.65
    0.61
    s
    0.61
     ahí
    0.60
     be
    0.59
    }\
    0.58
    ↵↵
    0.57
     jedn
    0.56
    4
    0.56
    }$
    0.55
    POSITIVE LOGITS
    ל
    1.00
    л
    0.83
    т
    0.80
    К
    0.79
    י
    0.76
    मध्ये
    0.67
    ו
    0.66
    𐰴
    0.64
    ין
    0.64
    ла
    0.63
    Activations Density 0.100%

    No Known Activations