Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1959
    Prev
    Next
    INDEX
    Explanations

    closing brackets and braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
     Said
    0.68
    iscono
    0.64
     начале
    0.63
     Claim
    0.63
     Comercial
    0.63
     及
    0.61
    暨
    0.60
    igh
    0.60
     gamme
    0.60
    she
    0.58
    POSITIVE LOGITS
    ]}
    1.29
    }}
    1.25
    }]
    1.24
     }]
    1.19
    |}
    1.17
    ]})
    1.16
    }])
    1.10
    ]]
    1.09
    }],
    1.06
    }]}
    1.05
    Activations Density 0.198%

    No Known Activations