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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 14227
    Prev
    Next
    INDEX
    Explanations

    tamper with

    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_16_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
     I
    0.97
     dogma
    0.95
     the
    0.86
     consumable
    0.86
     people
    0.83
    ).
    0.81
    )
    0.79
    ]
    0.79
    "]
    0.77
     there
    0.77
    POSITIVE LOGITS
    ре
    1.00
    𝘱
    0.96
    ра
    0.95
    он
    0.89
    k
    0.86
    מ
    0.86
    ra
    0.84
    𝘣
    0.84
    いる
    0.83
    ки
    0.83
    Activations Density 0.008%

    No Known Activations