© 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. 1795
    Prev
    Next
    INDEX
    Explanations

    Meridian, direction, history, scholarships, programs, date

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

    closing parentheses and quotes

    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
    لنا
    0.39
    스코
    0.36
    ناها
    0.35
     بودند
    0.35
    桷
    0.34
    }^{+},
    0.33
    GALAD
    0.33
    BIUM
    0.33
    كنولوجيا
    0.33
    스가
    0.33
    POSITIVE LOGITS
    ")
    0.48
    )
    0.46
    ）
    0.46
    ')
    0.41
    ”
    0.41
    })
    0.40
    」
    0.40
    ↵
    0.39
    ]
    0.37
    ">
    0.36
    Activations Density 0.022%

    No Known Activations