© 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. 31-GEMMASCOPE-2-RES-262K
    7. 8550
    Prev
    Next
    INDEX
    Explanations

    concepts and their roles

    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_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
    ک
    0.53
     staffers
    0.51
    在
    0.50
     correspondents
    0.49
    P
    0.48
    L
    0.48
    ],
    0.47
    سات
    0.47
    argent
    0.47
    J
    0.47
    POSITIVE LOGITS
     faci
    0.44
     phrase
    0.43
    饪
    0.43
     ге
    0.42
    ęcia
    0.42
     rivière
    0.42
    дени
    0.42
     heat
    0.41
     parcial
    0.41
     podido
    0.40
    Activations Density 0.001%

    No Known Activations