© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10435
    Prev
    Next
    INDEX
    Explanations

    black-and-white thinking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    \]
    2.25
    ),\
    2.22
    ],\
    2.11
    ্শন
    2.05
     \]
    2.05
    };\
    1.97
    },\
    1.94
    ለም
    1.91
    žno
    1.88
    اہم
    1.84
    POSITIVE LOGITS
    魎
    2.10
    s
    2.08
    .“
    1.82
     rep
    1.70
    ség
    1.67
    ો
    1.66
     forfeit
    1.63
    𝕖
    1.62
    sai
    1.59
    “
    1.58
    Activations Density 0.008%

    No Known Activations