© 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. 195438
    Prev
    Next
    INDEX
    Explanations

    authorized by, miss!, Island, far enough, patients within

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

    quantitative analysis and generation

    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
     مین
    0.44
     ویر
    0.44
     разби
    0.44
    ('$
    0.43
     ဖ
    0.42
    ]，
    0.42
     موسی
    0.41
     আগেই
    0.41
     شی
    0.40
    SignIn
    0.40
    POSITIVE LOGITS
    انيه
    0.57
    電腦
    0.52
    تون
    0.52
    }[\
    0.47
     utilising
    0.45
     stimul
    0.45
    雲
    0.45
     vektor
    0.44
     Möbius
    0.44
    ப்படுவத
    0.44
    Activations Density 0.001%

    No Known Activations